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

Dataset: Open Web Text

Neuron 662 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: 5.1398. Min Range: -5.1398

Max Act: 5.1398. Min Act: -0.1699

Data Index: 1126297 (Open Web Text)

Max Activating Token Index: 48

Text #1

Max Range: 5.1398. Min Range: -5.1398

Max Act: 5.1001. Min Act: -0.1700

Data Index: 5667779 (Open Web Text)

Max Activating Token Index: 370

Text #2

Max Range: 5.1398. Min Range: -5.1398

Max Act: 5.0220. Min Act: -0.1700

Data Index: 2553624 (Open Web Text)

Max Activating Token Index: 294

Text #3

Max Range: 5.1398. Min Range: -5.1398

Max Act: 5.0409. Min Act: -0.1700

Data Index: 1267455 (Open Web Text)

Max Activating Token Index: 826

Text #4

Max Range: 5.1398. Min Range: -5.1398

Max Act: 5.0151. Min Act: -0.1700

Data Index: 4914082 (Open Web Text)

Max Activating Token Index: 61

Text #5

Max Range: 5.1398. Min Range: -5.1398

Max Act: 5.0007. Min Act: -0.1700

Data Index: 5590878 (Open Web Text)

Max Activating Token Index: 245

Text #6

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.9469. Min Act: -0.1698

Data Index: 4242214 (Open Web Text)

Max Activating Token Index: 453

Text #7

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.9708. Min Act: -0.1700

Data Index: 2548253 (Open Web Text)

Max Activating Token Index: 314

Text #8

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.8890. Min Act: -0.1700

Data Index: 291517 (Open Web Text)

Max Activating Token Index: 311

Text #9

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.9442. Min Act: -0.1700

Data Index: 651754 (Open Web Text)

Max Activating Token Index: 324

Text #10

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.9347. Min Act: -0.1700

Data Index: 332711 (Open Web Text)

Max Activating Token Index: 516

Text #11

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.8935. Min Act: -0.1700

Data Index: 5545280 (Open Web Text)

Max Activating Token Index: 328

Text #12

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.8193. Min Act: -0.1700

Data Index: 8238910 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.8679. Min Act: -0.1700

Data Index: 5659823 (Open Web Text)

Max Activating Token Index: 390

Text #14

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.8239. Min Act: -0.1700

Data Index: 2411335 (Open Web Text)

Max Activating Token Index: 33

Text #15

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.8087. Min Act: -0.1700

Data Index: 1398191 (Open Web Text)

Max Activating Token Index: 797

Text #16

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.7661. Min Act: -0.1700

Data Index: 4035423 (Open Web Text)

Max Activating Token Index: 482

Text #17

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.7587. Min Act: -0.1700

Data Index: 271761 (Open Web Text)

Max Activating Token Index: 389

Text #18

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.8157. Min Act: -0.1700

Data Index: 4851727 (Open Web Text)

Max Activating Token Index: 358

Text #19

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.7706. Min Act: -0.1700

Data Index: 669451 (Open Web Text)

Max Activating Token Index: 279