< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2565 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.1329. Min Act: -0.1700

Data Index: 8094855 (Open Web Text)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0980. Min Act: -0.1700

Data Index: 2041500 (Open Web Text)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0940. Min Act: -0.1700

Data Index: 4739428 (Open Web Text)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0763. Min Act: -0.1700

Data Index: 5083215 (Open Web Text)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0614. Min Act: -0.1700

Data Index: 6417002 (Open Web Text)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0503. Min Act: -0.1700

Data Index: 1501226 (Open Web Text)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0485. Min Act: -0.1700

Data Index: 5313340 (Open Web Text)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0478. Min Act: -0.1700

Data Index: 2964415 (Open Web Text)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0517. Min Act: -0.1700

Data Index: 2943381 (Open Web Text)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0283. Min Act: -0.1700

Data Index: 1056287 (Open Web Text)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0296. Min Act: -0.1700

Data Index: 1939038 (Open Web Text)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0326. Min Act: -0.1700

Data Index: 5174320 (Open Web Text)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0292. Min Act: -0.1700

Data Index: 4848401 (Open Web Text)

Max Activating Token Index: 70

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0348. Min Act: -0.1700

Data Index: 5860318 (Open Web Text)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0393. Min Act: -0.1700

Data Index: 1684912 (Open Web Text)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0210. Min Act: -0.1700

Data Index: 6949371 (Open Web Text)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0181. Min Act: -0.1700

Data Index: 5105579 (Open Web Text)

Max Activating Token Index: 996

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0178. Min Act: -0.1700

Data Index: 3321604 (Open Web Text)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0225. Min Act: -0.1700

Data Index: 3400028 (Open Web Text)

Max Activating Token Index: 702

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.1329. Min Range: -2.1329

Max Act: 2.0196. Min Act: -0.1699

Data Index: 3642271 (Open Web Text)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #19