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

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

Neuron 3623 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.5896. Min Act: -0.0002

Data Index: 1041148 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.5208. Min Act: -0.0002

Data Index: 1202315 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3805. Min Act: -0.0002

Data Index: 336215 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3526. Min Act: -0.0002

Data Index: 387540 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.4380. Min Act: -0.0002

Data Index: 1018305 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3891. Min Act: -0.0002

Data Index: 1141184 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3300. Min Act: -0.0002

Data Index: 941748 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3099. Min Act: -0.0002

Data Index: 634354 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2730. Min Act: -0.0002

Data Index: 705021 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3769. Min Act: -0.0002

Data Index: 381094 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2639. Min Act: -0.0002

Data Index: 301112 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3388. Min Act: -0.0002

Data Index: 165678 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3673. Min Act: -0.0002

Data Index: 409507 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3282. Min Act: -0.0002

Data Index: 1199369 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3161. Min Act: -0.0002

Data Index: 1352914 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2471. Min Act: -0.0002

Data Index: 673828 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2327. Min Act: -0.0002

Data Index: 737585 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3064. Min Act: -0.0002

Data Index: 1114498 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2555. Min Act: -0.0002

Data Index: 260778 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.3022. Min Act: -0.0002

Data Index: 788311 (C4 (Web Text))

Max Activating Token Index: 938