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

Dataset: Open Web Text

Neuron 2042 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: 2.7427. Min Range: -2.7427

Max Act: 2.7253. Min Act: -0.1700

Data Index: 5204453 (Open Web Text)

Max Activating Token Index: 539

Text #1

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.7427. Min Act: -0.1700

Data Index: 5439186 (Open Web Text)

Max Activating Token Index: 655

Text #2

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.7223. Min Act: -0.1700

Data Index: 555778 (Open Web Text)

Max Activating Token Index: 901

Text #3

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6466. Min Act: -0.1700

Data Index: 5402021 (Open Web Text)

Max Activating Token Index: 207

Text #4

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6643. Min Act: -0.1700

Data Index: 5980186 (Open Web Text)

Max Activating Token Index: 309

Text #5

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6475. Min Act: -0.1700

Data Index: 2668659 (Open Web Text)

Max Activating Token Index: 941

Text #6

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6422. Min Act: -0.1700

Data Index: 3926900 (Open Web Text)

Max Activating Token Index: 535

Text #7

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6208. Min Act: -0.1700

Data Index: 4258198 (Open Web Text)

Max Activating Token Index: 522

Text #8

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6193. Min Act: -0.1700

Data Index: 685204 (Open Web Text)

Max Activating Token Index: 668

Text #9

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6195. Min Act: -0.1700

Data Index: 1042543 (Open Web Text)

Max Activating Token Index: 210

Text #10

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6156. Min Act: -0.1700

Data Index: 4382089 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6166. Min Act: -0.1700

Data Index: 7956265 (Open Web Text)

Max Activating Token Index: 535

Text #12

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6259. Min Act: -0.1700

Data Index: 5941478 (Open Web Text)

Max Activating Token Index: 349

Text #13

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6432. Min Act: -0.1700

Data Index: 5861876 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6271. Min Act: -0.1700

Data Index: 5583873 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6118. Min Act: -0.1700

Data Index: 5833993 (Open Web Text)

Max Activating Token Index: 344

Text #16

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6176. Min Act: -0.1700

Data Index: 7156280 (Open Web Text)

Max Activating Token Index: 349

Text #17

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6292. Min Act: -0.1700

Data Index: 7455639 (Open Web Text)

Max Activating Token Index: 1007

Text #18

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6077. Min Act: -0.1700

Data Index: 2824052 (Open Web Text)

Max Activating Token Index: 285

Text #19

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.6166. Min Act: -0.1700

Data Index: 555785 (Open Web Text)

Max Activating Token Index: 121