Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1276 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2469. Min Range: -2.2469

Max Act: 2.2469. Min Act: -0.0000

Data Index: 768434 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.9045. Min Act: -0.0000

Data Index: 367457 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 2.2469. Min Range: -2.2469

Max Act: 2.1067. Min Act: -0.0000

Data Index: 497894 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.8500. Min Act: -0.0000

Data Index: 1072835 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.7369. Min Act: -0.0000

Data Index: 616464 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.7302. Min Act: -0.0000

Data Index: 1486027 (Python Code)

Max Activating Token Index: 810

Text #6

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.8215. Min Act: -0.0000

Data Index: 1345705 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.6203. Min Act: -0.0000

Data Index: 1564778 (Python Code)

Max Activating Token Index: 979

Text #8

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.7382. Min Act: -0.0000

Data Index: 1141234 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.7234. Min Act: -0.0000

Data Index: 925854 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.6203. Min Act: -0.0000

Data Index: 1081059 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.6350. Min Act: -0.0000

Data Index: 346567 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.6363. Min Act: -0.0000

Data Index: 321952 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.4469. Min Act: -0.0000

Data Index: 163182 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.4701. Min Act: -0.0000

Data Index: 978368 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.5642. Min Act: -0.0000

Data Index: 1239995 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.3816. Min Act: -0.0000

Data Index: 747802 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1497327 (Python Code)

Max Activating Token Index: 54

Text #18

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.4811. Min Act: -0.0000

Data Index: 1399571 (Python Code)

Max Activating Token Index: 287

Text #19

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.3604. Min Act: -0.0000

Data Index: 1470390 (Python Code)

Max Activating Token Index: 516