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

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

Neuron 5049 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: 0.1194. Min Range: -0.1194

Max Act: 0.1194. Min Act: -0.0002

Data Index: 467910 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1132. Min Act: -0.0002

Data Index: 666667 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1188. Min Act: -0.0002

Data Index: 304735 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1130. Min Act: -0.0002

Data Index: 38714 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1165. Min Act: -0.0002

Data Index: 16972 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1099. Min Act: -0.0002

Data Index: 511965 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1127. Min Act: -0.0002

Data Index: 710226 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1166. Min Act: -0.0002

Data Index: 450411 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1147. Min Act: -0.0002

Data Index: 911968 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1150. Min Act: -0.0002

Data Index: 673274 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1045458 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1026798 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0955. Min Act: -0.0002

Data Index: 75203 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1269150 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1074. Min Act: -0.0002

Data Index: 240076 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1187. Min Act: -0.0002

Data Index: 340727 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0990. Min Act: -0.0002

Data Index: 746374 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1106. Min Act: -0.0002

Data Index: 86591 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0966. Min Act: -0.0002

Data Index: 768732 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0986. Min Act: -0.0002

Data Index: 62299 (C4 (Web Text))

Max Activating Token Index: 137