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

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

Neuron 1697 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: 2.8285. Min Range: -2.8285

Max Act: 2.8205. Min Act: -0.0000

Data Index: 77745 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.8285. Min Act: -0.0000

Data Index: 1107720 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.7082. Min Act: -0.0000

Data Index: 153881 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.4208. Min Act: -0.0000

Data Index: 257930 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.3762. Min Act: -0.0000

Data Index: 65626 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.3884. Min Act: -0.0000

Data Index: 820574 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.4668. Min Act: -0.0000

Data Index: 293817 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.3130. Min Act: -0.0000

Data Index: 1095907 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.3164. Min Act: -0.0000

Data Index: 152216 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.3159. Min Act: -0.0000

Data Index: 87721 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.3034. Min Act: -0.0000

Data Index: 31272 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.3182. Min Act: -0.0000

Data Index: 107819 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.3040. Min Act: -0.0000

Data Index: 1321164 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.0021. Min Act: -0.0000

Data Index: 1096699 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.2408. Min Act: -0.0000

Data Index: 1222833 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.3640. Min Act: -0.0000

Data Index: 610468 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.1262. Min Act: -0.0000

Data Index: 596137 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.2356. Min Act: -0.0000

Data Index: 996365 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.2194. Min Act: -0.0000

Data Index: 195446 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 2.8285. Min Range: -2.8285

Max Act: 2.2166. Min Act: -0.0000

Data Index: 277639 (C4 (Web Text))

Max Activating Token Index: 270