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

Dataset: Open Web Text

Neuron 458 in Layer 6

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: 3.8520. Min Range: -3.8520

Max Act: 3.8520. Min Act: -0.1700

Data Index: 6481402 (Open Web Text)

Max Activating Token Index: 624

Text #1

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.7171. Min Act: -0.1700

Data Index: 2525102 (Open Web Text)

Max Activating Token Index: 190

Text #2

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.6601. Min Act: -0.1700

Data Index: 1445716 (Open Web Text)

Max Activating Token Index: 912

Text #3

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.6217. Min Act: -0.1700

Data Index: 2207982 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.6042. Min Act: -0.1700

Data Index: 1227437 (Open Web Text)

Max Activating Token Index: 433

Text #5

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.6083. Min Act: -0.1700

Data Index: 8588419 (Open Web Text)

Max Activating Token Index: 206

Text #6

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.6185. Min Act: -0.1700

Data Index: 6712310 (Open Web Text)

Max Activating Token Index: 721

Text #7

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.5971. Min Act: -0.1700

Data Index: 5947457 (Open Web Text)

Max Activating Token Index: 595

Text #8

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.5837. Min Act: -0.1700

Data Index: 6587580 (Open Web Text)

Max Activating Token Index: 35

Text #9

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.5973. Min Act: -0.1700

Data Index: 4893773 (Open Web Text)

Max Activating Token Index: 907

Text #10

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.5615. Min Act: -0.1700

Data Index: 6663272 (Open Web Text)

Max Activating Token Index: 278

Text #11

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.5638. Min Act: -0.1700

Data Index: 2915471 (Open Web Text)

Max Activating Token Index: 981

Text #12

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.5162. Min Act: -0.1700

Data Index: 1066287 (Open Web Text)

Max Activating Token Index: 896

Text #13

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.5501. Min Act: -0.1700

Data Index: 595284 (Open Web Text)

Max Activating Token Index: 954

Text #14

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.5283. Min Act: -0.1700

Data Index: 2139016 (Open Web Text)

Max Activating Token Index: 330

Text #15

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.5352. Min Act: -0.1700

Data Index: 2618822 (Open Web Text)

Max Activating Token Index: 982

Text #16

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.5213. Min Act: -0.1700

Data Index: 1283278 (Open Web Text)

Max Activating Token Index: 543

Text #17

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.5094. Min Act: -0.1700

Data Index: 4777629 (Open Web Text)

Max Activating Token Index: 383

Text #18

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.5090. Min Act: -0.1700

Data Index: 4590570 (Open Web Text)

Max Activating Token Index: 886

Text #19

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.5318. Min Act: -0.1700

Data Index: 6577394 (Open Web Text)

Max Activating Token Index: 595