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

Dataset: Open Web Text

Neuron 2016 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: 1.7473. Min Range: -1.7473

Max Act: 1.7473. Min Act: -0.1655

Data Index: 4705603 (Open Web Text)

Max Activating Token Index: 89

Text #1

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.7322. Min Act: -0.0655

Data Index: 4969382 (Open Web Text)

Max Activating Token Index: 174

Text #2

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.7240. Min Act: -0.0309

Data Index: 2615778 (Open Web Text)

Max Activating Token Index: 184

Text #3

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6977. Min Act: -0.0706

Data Index: 6672275 (Open Web Text)

Max Activating Token Index: 696

Text #4

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6831. Min Act: -0.1597

Data Index: 8273185 (Open Web Text)

Max Activating Token Index: 849

Text #5

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6667. Min Act: -0.1697

Data Index: 3160990 (Open Web Text)

Max Activating Token Index: 958

Text #6

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6352. Min Act: -0.1609

Data Index: 1052030 (Open Web Text)

Max Activating Token Index: 506

Text #7

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6371. Min Act: -0.1571

Data Index: 4365629 (Open Web Text)

Max Activating Token Index: 285

Text #8

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6350. Min Act: -0.1699

Data Index: 3184511 (Open Web Text)

Max Activating Token Index: 372

Text #9

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6280. Min Act: -0.1568

Data Index: 6079692 (Open Web Text)

Max Activating Token Index: 883

Text #10

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6276. Min Act: -0.1697

Data Index: 7551374 (Open Web Text)

Max Activating Token Index: 214

Text #11

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6241. Min Act: -0.1631

Data Index: 2517652 (Open Web Text)

Max Activating Token Index: 223

Text #12

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6181. Min Act: -0.1415

Data Index: 2925659 (Open Web Text)

Max Activating Token Index: 688

Text #13

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6148. Min Act: -0.0609

Data Index: 8068234 (Open Web Text)

Max Activating Token Index: 356

Text #14

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6139. Min Act: -0.1674

Data Index: 1710958 (Open Web Text)

Max Activating Token Index: 288

Text #15

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6206. Min Act: -0.1429

Data Index: 2925626 (Open Web Text)

Max Activating Token Index: 956

Text #16

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6150. Min Act: -0.1696

Data Index: 4184799 (Open Web Text)

Max Activating Token Index: 529

Text #17

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6053. Min Act: -0.0781

Data Index: 7955811 (Open Web Text)

Max Activating Token Index: 552

Text #18

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6047. Min Act: -0.1658

Data Index: 5670535 (Open Web Text)

Max Activating Token Index: 478

Text #19

Max Range: 1.7473. Min Range: -1.7473

Max Act: 1.6037. Min Act: -0.1571

Data Index: 5259021 (Open Web Text)

Max Activating Token Index: 1021