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

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

Neuron 1420 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0002

Data Index: 479889 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0002

Data Index: 702172 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0002

Data Index: 798461 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0046. Min Act: -0.0002

Data Index: 183868 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0046. Min Act: -0.0002

Data Index: 1320010 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0002

Data Index: 382974 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0002

Data Index: 143168 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0002

Data Index: 684799 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0002

Data Index: 322370 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0046. Min Act: -0.0002

Data Index: 471996 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0002

Data Index: 98768 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0002

Data Index: 690984 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0002

Data Index: 632307 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1173322 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1283355 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0002

Data Index: 774965 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0002

Data Index: 461630 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0002

Data Index: 895313 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0002

Data Index: 540908 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0002

Data Index: 701311 (C4 (Web Text))

Max Activating Token Index: 738