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

Dataset: Open Web Text

Neuron 2628 in Layer 0

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: 1.4914. Min Range: -1.4914

Max Act: 1.4914. Min Act: -0.1682

Data Index: 6789422 (Open Web Text)

Max Activating Token Index: 617

Text #1

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.4333. Min Act: -0.1699

Data Index: 6789420 (Open Web Text)

Max Activating Token Index: 95

Text #2

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3676. Min Act: -0.1467

Data Index: 2546438 (Open Web Text)

Max Activating Token Index: 803

Text #3

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3723. Min Act: -0.1614

Data Index: 7965219 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3646. Min Act: -0.1689

Data Index: 2426628 (Open Web Text)

Max Activating Token Index: 595

Text #5

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3640. Min Act: -0.1686

Data Index: 7981973 (Open Web Text)

Max Activating Token Index: 372

Text #6

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3375. Min Act: -0.1414

Data Index: 1560144 (Open Web Text)

Max Activating Token Index: 610

Text #7

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3485. Min Act: -0.1668

Data Index: 7851715 (Open Web Text)

Max Activating Token Index: 411

Text #8

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3455. Min Act: -0.1491

Data Index: 4415059 (Open Web Text)

Max Activating Token Index: 539

Text #9

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3322. Min Act: -0.1568

Data Index: 2817842 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3291. Min Act: -0.1490

Data Index: 1569895 (Open Web Text)

Max Activating Token Index: 605

Text #11

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3280. Min Act: -0.1144

Data Index: 1785344 (Open Web Text)

Max Activating Token Index: 673

Text #12

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3260. Min Act: -0.1684

Data Index: 6061028 (Open Web Text)

Max Activating Token Index: 705

Text #13

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3254. Min Act: -0.1645

Data Index: 5759354 (Open Web Text)

Max Activating Token Index: 179

Text #14

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3262. Min Act: -0.1642

Data Index: 1432000 (Open Web Text)

Max Activating Token Index: 233

Text #15

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3274. Min Act: -0.1399

Data Index: 2817839 (Open Web Text)

Max Activating Token Index: 750

Text #16

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3311. Min Act: -0.1595

Data Index: 7533789 (Open Web Text)

Max Activating Token Index: 323

Text #17

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3186. Min Act: -0.1686

Data Index: 5516325 (Open Web Text)

Max Activating Token Index: 993

Text #18

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3279. Min Act: -0.1677

Data Index: 2505580 (Open Web Text)

Max Activating Token Index: 357

Text #19

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3180. Min Act: -0.1694

Data Index: 4699036 (Open Web Text)

Max Activating Token Index: 245