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

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

Neuron 3247 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1222. Min Act: -0.0001

Data Index: 601228 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1118. Min Act: -0.0001

Data Index: 352328 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1120. Min Act: -0.0001

Data Index: 851683 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1041. Min Act: -0.0001

Data Index: 577861 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1074. Min Act: -0.0001

Data Index: 722118 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1009. Min Act: -0.0001

Data Index: 429711 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1034. Min Act: -0.0001

Data Index: 860547 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1007. Min Act: -0.0001

Data Index: 215152 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1425453 (Python Code)

Max Activating Token Index: 1014

Text #9

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0921. Min Act: -0.0001

Data Index: 360696 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1005. Min Act: -0.0001

Data Index: 108961 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1033. Min Act: -0.0001

Data Index: 915616 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1089730 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1244965 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.1039. Min Act: -0.0001

Data Index: 157751 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0914. Min Act: -0.0001

Data Index: 216645 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0939. Min Act: -0.0001

Data Index: 261852 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0885. Min Act: -0.0001

Data Index: 889800 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0866. Min Act: -0.0001

Data Index: 184793 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.1222. Min Range: -0.1222

Max Act: 0.0924. Min Act: -0.0001

Data Index: 243318 (C4 (Web Text))

Max Activating Token Index: 807