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

Dataset: Open Web Text

Neuron 2613 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: 3.0228. Min Range: -3.0228

Max Act: 3.0228. Min Act: -0.1700

Data Index: 216996 (Open Web Text)

Max Activating Token Index: 977

Text #1

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9850. Min Act: -0.1700

Data Index: 5510683 (Open Web Text)

Max Activating Token Index: 956

Text #2

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9923. Min Act: -0.1700

Data Index: 5942078 (Open Web Text)

Max Activating Token Index: 445

Text #3

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9591. Min Act: -0.1700

Data Index: 6782140 (Open Web Text)

Max Activating Token Index: 462

Text #4

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9439. Min Act: -0.1700

Data Index: 149987 (Open Web Text)

Max Activating Token Index: 667

Text #5

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9622. Min Act: -0.1700

Data Index: 940203 (Open Web Text)

Max Activating Token Index: 409

Text #6

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9246. Min Act: -0.1700

Data Index: 4549101 (Open Web Text)

Max Activating Token Index: 437

Text #7

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9243. Min Act: -0.1700

Data Index: 4011169 (Open Web Text)

Max Activating Token Index: 702

Text #8

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9276. Min Act: -0.1700

Data Index: 414333 (Open Web Text)

Max Activating Token Index: 971

Text #9

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9329. Min Act: -0.1700

Data Index: 3457643 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9443. Min Act: -0.1700

Data Index: 6503507 (Open Web Text)

Max Activating Token Index: 514

Text #11

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9344. Min Act: -0.1700

Data Index: 8609121 (Open Web Text)

Max Activating Token Index: 438

Text #12

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9303. Min Act: -0.1700

Data Index: 7266816 (Open Web Text)

Max Activating Token Index: 295

Text #13

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9067. Min Act: -0.1700

Data Index: 3722954 (Open Web Text)

Max Activating Token Index: 218

Text #14

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9131. Min Act: -0.1700

Data Index: 3997526 (Open Web Text)

Max Activating Token Index: 471

Text #15

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9028. Min Act: -0.1700

Data Index: 1269321 (Open Web Text)

Max Activating Token Index: 367

Text #16

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9163. Min Act: -0.1700

Data Index: 6641559 (Open Web Text)

Max Activating Token Index: 314

Text #17

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9137. Min Act: -0.1700

Data Index: 2252125 (Open Web Text)

Max Activating Token Index: 970

Text #18

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9148. Min Act: -0.1700

Data Index: 417228 (Open Web Text)

Max Activating Token Index: 741

Text #19

Max Range: 3.0228. Min Range: -3.0228

Max Act: 2.9052. Min Act: -0.1700

Data Index: 5536359 (Open Web Text)

Max Activating Token Index: 452