Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 111 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1243. Min Act: -0.0002

Data Index: 843490 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1228. Min Act: -0.0002

Data Index: 426183 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1160. Min Act: -0.0002

Data Index: 389923 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1114. Min Act: -0.0002

Data Index: 871306 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1147. Min Act: -0.0001

Data Index: 657665 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1206813 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0966. Min Act: -0.0001

Data Index: 634170 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1013. Min Act: -0.0002

Data Index: 316911 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1015. Min Act: -0.0002

Data Index: 402318 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1004. Min Act: -0.0002

Data Index: 617481 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1003. Min Act: -0.0001

Data Index: 4636 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0996. Min Act: -0.0001

Data Index: 959870 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0988. Min Act: -0.0001

Data Index: 128462 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0976. Min Act: -0.0002

Data Index: 614437 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0967. Min Act: -0.0002

Data Index: 273233 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0902. Min Act: -0.0001

Data Index: 229538 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0903. Min Act: -0.0002

Data Index: 85256 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1344883 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0916. Min Act: -0.0001

Data Index: 40997 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0918. Min Act: -0.0001

Data Index: 883657 (C4 (Web Text))

Max Activating Token Index: 609