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

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

Neuron 4657 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1458. Min Act: -0.0002

Data Index: 1345797 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1256. Min Act: -0.0002

Data Index: 1248460 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1251. Min Act: -0.0002

Data Index: 333354 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1255. Min Act: -0.0002

Data Index: 479456 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1282579 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1154. Min Act: -0.0002

Data Index: 910983 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1132. Min Act: -0.0002

Data Index: 881796 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1135. Min Act: -0.0002

Data Index: 1338603 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1111. Min Act: -0.0002

Data Index: 648622 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1110. Min Act: -0.0002

Data Index: 220175 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1088. Min Act: -0.0002

Data Index: 330297 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1095. Min Act: -0.0002

Data Index: 1305953 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1022. Min Act: -0.0002

Data Index: 590424 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1043. Min Act: -0.0002

Data Index: 1023099 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1217228 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1001. Min Act: -0.0002

Data Index: 968984 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1038. Min Act: -0.0002

Data Index: 507363 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1029. Min Act: -0.0002

Data Index: 182529 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1026. Min Act: -0.0002

Data Index: 406270 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1023. Min Act: -0.0002

Data Index: 354988 (C4 (Web Text))

Max Activating Token Index: 554