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

Dataset: Open Web Text

Neuron 917 in Layer 1

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: 1.0983. Min Range: -1.0983

Max Act: 1.0983. Min Act: -0.1512

Data Index: 6120211 (Open Web Text)

Max Activating Token Index: 403

Text #1

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0929. Min Act: -0.1695

Data Index: 7564755 (Open Web Text)

Max Activating Token Index: 498

Text #2

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0905. Min Act: -0.1684

Data Index: 2381038 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0826. Min Act: -0.1621

Data Index: 7818840 (Open Web Text)

Max Activating Token Index: 451

Text #4

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0810. Min Act: -0.1476

Data Index: 6339098 (Open Web Text)

Max Activating Token Index: 430

Text #5

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0801. Min Act: -0.1126

Data Index: 2231853 (Open Web Text)

Max Activating Token Index: 409

Text #6

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0652. Min Act: -0.1486

Data Index: 7025160 (Open Web Text)

Max Activating Token Index: 510

Text #7

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0756. Min Act: -0.1690

Data Index: 5240060 (Open Web Text)

Max Activating Token Index: 71

Text #8

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0626. Min Act: -0.1658

Data Index: 2298424 (Open Web Text)

Max Activating Token Index: 327

Text #9

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0630. Min Act: -0.1456

Data Index: 6615292 (Open Web Text)

Max Activating Token Index: 406

Text #10

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0626. Min Act: -0.1503

Data Index: 6930779 (Open Web Text)

Max Activating Token Index: 405

Text #11

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0575. Min Act: -0.1615

Data Index: 6959290 (Open Web Text)

Max Activating Token Index: 440

Text #12

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0413. Min Act: -0.1362

Data Index: 5267960 (Open Web Text)

Max Activating Token Index: 401

Text #13

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0440. Min Act: -0.1544

Data Index: 2341959 (Open Web Text)

Max Activating Token Index: 339

Text #14

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0457. Min Act: -0.1575

Data Index: 6829524 (Open Web Text)

Max Activating Token Index: 468

Text #15

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0553. Min Act: -0.1508

Data Index: 4433322 (Open Web Text)

Max Activating Token Index: 394

Text #16

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0427. Min Act: -0.1497

Data Index: 3255334 (Open Web Text)

Max Activating Token Index: 36

Text #17

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0480. Min Act: -0.1544

Data Index: 4600260 (Open Web Text)

Max Activating Token Index: 467

Text #18

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0379. Min Act: -0.1490

Data Index: 1297631 (Open Web Text)

Max Activating Token Index: 425

Text #19

Max Range: 1.0983. Min Range: -1.0983

Max Act: 1.0335. Min Act: -0.1176

Data Index: 4509394 (Open Web Text)

Max Activating Token Index: 507