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

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

Neuron 1304 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1270. Min Act: -0.0003

Data Index: 908767 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1212. Min Act: -0.0002

Data Index: 596349 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1207. Min Act: -0.0003

Data Index: 314698 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1146. Min Act: -0.0003

Data Index: 880327 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1169. Min Act: -0.0002

Data Index: 1326923 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1171. Min Act: -0.0002

Data Index: 119060 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1148. Min Act: -0.0002

Data Index: 94605 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1164. Min Act: -0.0002

Data Index: 426329 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1138. Min Act: -0.0002

Data Index: 662733 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1120. Min Act: -0.0003

Data Index: 693344 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1138. Min Act: -0.0003

Data Index: 1089811 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1137. Min Act: -0.0003

Data Index: 1097567 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1124. Min Act: -0.0003

Data Index: 582766 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1101. Min Act: -0.0003

Data Index: 719017 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1083. Min Act: -0.0003

Data Index: 1097689 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1102. Min Act: -0.0003

Data Index: 1019756 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1108. Min Act: -0.0002

Data Index: 273168 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1055. Min Act: -0.0002

Data Index: 55158 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1126. Min Act: -0.0003

Data Index: 1355458 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1089. Min Act: -0.0003

Data Index: 1293206 (C4 (Web Text))

Max Activating Token Index: 16