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

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

Neuron 2880 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: 0.1156. Min Range: -0.1156

Max Act: 0.1104. Min Act: -0.0002

Data Index: 338737 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1197368 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1081. Min Act: -0.0002

Data Index: 108354 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1156. Min Act: -0.0002

Data Index: 635377 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1045. Min Act: -0.0002

Data Index: 317086 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1069. Min Act: -0.0002

Data Index: 231975 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1034. Min Act: -0.0002

Data Index: 269056 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1021. Min Act: -0.0002

Data Index: 209803 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0970. Min Act: -0.0002

Data Index: 767173 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1005. Min Act: -0.0002

Data Index: 811638 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1058195 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1023. Min Act: -0.0002

Data Index: 231410 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0984. Min Act: -0.0002

Data Index: 430420 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0973. Min Act: -0.0002

Data Index: 427315 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0974. Min Act: -0.0002

Data Index: 737610 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0964. Min Act: -0.0002

Data Index: 200143 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0963. Min Act: -0.0002

Data Index: 562805 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0963. Min Act: -0.0002

Data Index: 734421 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0954. Min Act: -0.0002

Data Index: 461785 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1114153 (C4 (Web Text))

Max Activating Token Index: 707