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

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

Neuron 3399 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1317141 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1176234 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1093704 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1245602 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6690. Min Act: -0.0000

Data Index: 872963 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6891. Min Act: -0.0000

Data Index: 943447 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6263. Min Act: -0.0000

Data Index: 779491 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6460. Min Act: -0.0000

Data Index: 38294 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6605. Min Act: -0.0000

Data Index: 232858 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6120. Min Act: -0.0000

Data Index: 89921 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6307. Min Act: -0.0000

Data Index: 450957 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6380. Min Act: -0.0000

Data Index: 726284 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1083272 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.5821. Min Act: -0.0000

Data Index: 332389 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1144651 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1145313 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.5889. Min Act: -0.0000

Data Index: 152220 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1143662 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.5614. Min Act: -0.0000

Data Index: 556706 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1140398 (C4 (Web Text))

Max Activating Token Index: 360