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

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

Neuron 3438 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.5156. Min Act: -0.0000

Data Index: 356876 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4523. Min Act: -0.0000

Data Index: 683164 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4106. Min Act: -0.0000

Data Index: 297754 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1248936 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1085606 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3851. Min Act: -0.0000

Data Index: 460505 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3298. Min Act: -0.0000

Data Index: 109701 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3216. Min Act: -0.0000

Data Index: 786335 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3528. Min Act: -0.0000

Data Index: 823520 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3557. Min Act: -0.0000

Data Index: 27204 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1163818 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1456 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3033. Min Act: -0.0000

Data Index: 937887 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3305. Min Act: -0.0000

Data Index: 503878 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3281. Min Act: -0.0000

Data Index: 132616 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3029. Min Act: -0.0000

Data Index: 144488 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3219. Min Act: -0.0000

Data Index: 924973 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3134. Min Act: -0.0000

Data Index: 76439 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3129. Min Act: -0.0000

Data Index: 714283 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1145819 (C4 (Web Text))

Max Activating Token Index: 481