Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3474 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.4466. Min Act: -0.0003

Data Index: 312699 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.4434. Min Act: -0.0003

Data Index: 298379 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.4201. Min Act: -0.0003

Data Index: 722390 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3682. Min Act: -0.0003

Data Index: 1304171 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3704. Min Act: -0.0003

Data Index: 1135200 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3321. Min Act: -0.0003

Data Index: 175817 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3411. Min Act: -0.0003

Data Index: 293115 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3411. Min Act: -0.0003

Data Index: 879852 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3496. Min Act: -0.0003

Data Index: 61877 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3379. Min Act: -0.0002

Data Index: 862100 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3284. Min Act: -0.0003

Data Index: 1249093 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3496. Min Act: -0.0003

Data Index: 530246 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3339. Min Act: -0.0003

Data Index: 1320293 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3480. Min Act: -0.0003

Data Index: 549431 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3156. Min Act: -0.0003

Data Index: 143783 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3255. Min Act: -0.0003

Data Index: 689009 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3339. Min Act: -0.0003

Data Index: 194234 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3229. Min Act: -0.0003

Data Index: 380688 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3435. Min Act: -0.0003

Data Index: 525107 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3418. Min Act: -0.0002

Data Index: 620377 (C4 (Web Text))

Max Activating Token Index: 695