Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2145 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1548. Min Act: -0.0003

Data Index: 845153 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1387. Min Act: -0.0003

Data Index: 379240 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1511. Min Act: -0.0003

Data Index: 1057371 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1019. Min Act: -0.0003

Data Index: 1324521 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1360. Min Act: -0.0003

Data Index: 682849 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1267. Min Act: -0.0003

Data Index: 722810 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1211. Min Act: -0.0003

Data Index: 127120 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1245. Min Act: -0.0003

Data Index: 129455 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1221. Min Act: -0.0003

Data Index: 314286 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1210. Min Act: -0.0003

Data Index: 802983 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1175. Min Act: -0.0003

Data Index: 1197051 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1291. Min Act: -0.0003

Data Index: 1161769 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1075. Min Act: -0.0003

Data Index: 1088528 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1198. Min Act: -0.0003

Data Index: 327090 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1172. Min Act: -0.0003

Data Index: 1322042 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1275. Min Act: -0.0003

Data Index: 170466 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1095. Min Act: -0.0003

Data Index: 1056720 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1121. Min Act: -0.0003

Data Index: 756286 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1199. Min Act: -0.0003

Data Index: 733259 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1141. Min Act: -0.0003

Data Index: 282093 (C4 (Web Text))

Max Activating Token Index: 400