Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5373 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.3805. Min Act: -0.0000

Data Index: 217937 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.3752. Min Act: -0.0000

Data Index: 163005 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.3464. Min Act: -0.0000

Data Index: 544856 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.3474. Min Act: -0.0000

Data Index: 519205 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1256814 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.3159. Min Act: -0.0000

Data Index: 80588 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1285827 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1182254 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.3070. Min Act: -0.0000

Data Index: 77647 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.2879. Min Act: -0.0000

Data Index: 657751 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.2884. Min Act: -0.0000

Data Index: 827923 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1309612 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.3065. Min Act: -0.0000

Data Index: 745482 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1491916 (Python Code)

Max Activating Token Index: 219

Text #14

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1025895 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.3103. Min Act: -0.0000

Data Index: 720458 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.2994. Min Act: -0.0000

Data Index: 107569 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.3005. Min Act: -0.0000

Data Index: 136171 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.2854. Min Act: -0.0000

Data Index: 248630 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.3805. Min Range: -0.3805

Max Act: 0.2956. Min Act: -0.0000

Data Index: 373840 (C4 (Web Text))

Max Activating Token Index: 740