Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2967 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1331. Min Act: -0.0002

Data Index: 1141139 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1313. Min Act: -0.0002

Data Index: 978422 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1273. Min Act: -0.0002

Data Index: 702274 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1371. Min Act: -0.0002

Data Index: 1002623 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1196. Min Act: -0.0002

Data Index: 1047087 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1164. Min Act: -0.0002

Data Index: 964475 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1057. Min Act: -0.0002

Data Index: 802112 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1170. Min Act: -0.0002

Data Index: 276447 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1083. Min Act: -0.0002

Data Index: 776383 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1072. Min Act: -0.0002

Data Index: 52012 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1131. Min Act: -0.0002

Data Index: 981955 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0916. Min Act: -0.0002

Data Index: 451895 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0994. Min Act: -0.0002

Data Index: 686446 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1057. Min Act: -0.0002

Data Index: 908827 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1086. Min Act: -0.0002

Data Index: 113742 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1021. Min Act: -0.0002

Data Index: 118022 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1119. Min Act: -0.0002

Data Index: 823161 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1053. Min Act: -0.0002

Data Index: 1005649 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0970. Min Act: -0.0002

Data Index: 682740 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0964. Min Act: -0.0002

Data Index: 1011764 (C4 (Web Text))

Max Activating Token Index: 842