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

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

Neuron 3484 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3281. Min Range: -5.3281

Max Act: 5.3281. Min Act: -0.0001

Data Index: 508962 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.6011. Min Act: -0.0001

Data Index: 70745 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.3617. Min Act: -0.0001

Data Index: 892182 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.2645. Min Act: -0.0001

Data Index: 555209 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.2330. Min Act: -0.0001

Data Index: 782094 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.4224. Min Act: -0.0001

Data Index: 544089 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.3225. Min Act: -0.0001

Data Index: 862084 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.1239. Min Act: -0.0001

Data Index: 1126504 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 5.3281. Min Range: -5.3281

Max Act: 3.5956. Min Act: -0.0001

Data Index: 1128954 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 5.3281. Min Range: -5.3281

Max Act: 3.7366. Min Act: -0.0001

Data Index: 1263778 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.2156. Min Act: -0.0001

Data Index: 172421 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.0119. Min Act: -0.0001

Data Index: 212815 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.0305. Min Act: -0.0001

Data Index: 1176449 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 5.3281. Min Range: -5.3281

Max Act: 3.8741. Min Act: -0.0001

Data Index: 290988 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 5.3281. Min Range: -5.3281

Max Act: 3.9353. Min Act: -0.0001

Data Index: 589375 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 5.3281. Min Range: -5.3281

Max Act: 3.7681. Min Act: -0.0001

Data Index: 1064343 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.0479. Min Act: -0.0001

Data Index: 1327480 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.1959. Min Act: -0.0001

Data Index: 107957 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 5.3281. Min Range: -5.3281

Max Act: 3.9913. Min Act: -0.0001

Data Index: 1185675 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 5.3281. Min Range: -5.3281

Max Act: 3.9516. Min Act: -0.0001

Data Index: 792073 (C4 (Web Text))

Max Activating Token Index: 296