< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 235 in Layer 5

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: 2.7238. Min Range: -2.7238

Max Act: 2.6957. Min Act: -0.1700

Data Index: 8450511 (Open Web Text)

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.7185. Min Act: -0.1700

Data Index: 2329038 (Open Web Text)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6999. Min Act: -0.1700

Data Index: 1687936 (Open Web Text)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.7238. Min Act: -0.1700

Data Index: 6265719 (Open Web Text)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6749. Min Act: -0.1700

Data Index: 3696092 (Open Web Text)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6658. Min Act: -0.1700

Data Index: 8714377 (Open Web Text)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6548. Min Act: -0.1700

Data Index: 519878 (Open Web Text)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6543. Min Act: -0.1700

Data Index: 4044170 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6350. Min Act: -0.1700

Data Index: 3820429 (Open Web Text)

Max Activating Token Index: 633

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6403. Min Act: -0.1700

Data Index: 894068 (Open Web Text)

Max Activating Token Index: 608

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6513. Min Act: -0.1700

Data Index: 1511828 (Open Web Text)

Max Activating Token Index: 676

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6414. Min Act: -0.1700

Data Index: 5781472 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6701. Min Act: -0.1700

Data Index: 6718056 (Open Web Text)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6391. Min Act: -0.1700

Data Index: 5669040 (Open Web Text)

Max Activating Token Index: 963

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6250. Min Act: -0.1700

Data Index: 398089 (Open Web Text)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6149. Min Act: -0.1700

Data Index: 1524477 (Open Web Text)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6356. Min Act: -0.1700

Data Index: 6116558 (Open Web Text)

Max Activating Token Index: 468

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6316. Min Act: -0.1700

Data Index: 425819 (Open Web Text)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6236. Min Act: -0.1700

Data Index: 4128832 (Open Web Text)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.7238. Min Range: -2.7238

Max Act: 2.6254. Min Act: -0.1700

Data Index: 4803555 (Open Web Text)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #19