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

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

Neuron 4699 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: 0.1181. Min Range: -0.1181

Max Act: 0.1181. Min Act: -0.0002

Data Index: 901813 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1149. Min Act: -0.0002

Data Index: 126025 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1102. Min Act: -0.0002

Data Index: 1190046 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1260201 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1075. Min Act: -0.0002

Data Index: 1071450 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1061. Min Act: -0.0002

Data Index: 1108482 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1112809 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1041. Min Act: -0.0002

Data Index: 248814 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1023. Min Act: -0.0002

Data Index: 488835 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0977. Min Act: -0.0002

Data Index: 241896 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1005. Min Act: -0.0002

Data Index: 187491 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1077685 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1029. Min Act: -0.0002

Data Index: 250486 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1153013 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0988. Min Act: -0.0002

Data Index: 976723 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1314332 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0930. Min Act: -0.0002

Data Index: 774475 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0966. Min Act: -0.0002

Data Index: 969011 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0923. Min Act: -0.0002

Data Index: 204364 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0918. Min Act: -0.0002

Data Index: 677833 (C4 (Web Text))

Max Activating Token Index: 1003