< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1046 in Layer 3

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: 2.8580. Min Range: -2.8580

Max Act: 2.8580. Min Act: -0.1700

Data Index: 7410178 (Open Web Text)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.8083. Min Act: -0.1700

Data Index: 1083878 (Open Web Text)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7960. Min Act: -0.1700

Data Index: 2475566 (Open Web Text)

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7680. Min Act: -0.1700

Data Index: 1062764 (Open Web Text)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7724. Min Act: -0.1700

Data Index: 7788827 (Open Web Text)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7534. Min Act: -0.1700

Data Index: 3509582 (Open Web Text)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7476. Min Act: -0.1700

Data Index: 5131496 (Open Web Text)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7292. Min Act: -0.1700

Data Index: 6193547 (Open Web Text)

Max Activating Token Index: 412

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7321. Min Act: -0.1700

Data Index: 7586385 (Open Web Text)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7243. Min Act: -0.1700

Data Index: 5439203 (Open Web Text)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7643. Min Act: -0.1693

Data Index: 6193539 (Open Web Text)

Max Activating Token Index: 451

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7372. Min Act: -0.1700

Data Index: 2085839 (Open Web Text)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7473. Min Act: -0.1700

Data Index: 3509583 (Open Web Text)

Max Activating Token Index: 546

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7232. Min Act: -0.1700

Data Index: 6193545 (Open Web Text)

Max Activating Token Index: 282

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7235. Min Act: -0.1700

Data Index: 6409940 (Open Web Text)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7006. Min Act: -0.1700

Data Index: 6942519 (Open Web Text)

Max Activating Token Index: 751

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7020. Min Act: -0.1700

Data Index: 6193551 (Open Web Text)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.6978. Min Act: -0.1700

Data Index: 1784559 (Open Web Text)

Max Activating Token Index: 711

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7369. Min Act: -0.1700

Data Index: 6687638 (Open Web Text)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8580. Min Range: -2.8580

Max Act: 2.7205. Min Act: -0.1700

Data Index: 6193534 (Open Web Text)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #19