Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 226 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1168. Min Act: -0.0006

Data Index: 265453 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1155. Min Act: -0.0006

Data Index: 507620 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1166. Min Act: -0.0006

Data Index: 1224026 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1116. Min Act: -0.0006

Data Index: 965406 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1069. Min Act: -0.0006

Data Index: 808533 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1100. Min Act: -0.0006

Data Index: 1272853 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1069. Min Act: -0.0006

Data Index: 404445 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1008. Min Act: -0.0006

Data Index: 393263 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1047. Min Act: -0.0006

Data Index: 99324 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1036. Min Act: -0.0006

Data Index: 720554 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0992. Min Act: -0.0006

Data Index: 599308 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1037. Min Act: -0.0006

Data Index: 423077 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1027. Min Act: -0.0006

Data Index: 102695 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1025. Min Act: -0.0006

Data Index: 320937 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1064. Min Act: -0.0006

Data Index: 1194855 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1065. Min Act: -0.0006

Data Index: 31208 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0969. Min Act: -0.0006

Data Index: 1111647 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1010. Min Act: -0.0006

Data Index: 780143 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0997. Min Act: -0.0006

Data Index: 563379 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0999. Min Act: -0.0006

Data Index: 106514 (C4 (Web Text))

Max Activating Token Index: 922