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

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

Neuron 5001 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1329. Min Act: -0.0002

Data Index: 1266778 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1296. Min Act: -0.0003

Data Index: 696525 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1233. Min Act: -0.0002

Data Index: 39378 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1215. Min Act: -0.0003

Data Index: 765857 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1216. Min Act: -0.0002

Data Index: 797530 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1130. Min Act: -0.0003

Data Index: 311381 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1147. Min Act: -0.0003

Data Index: 1169160 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1142. Min Act: -0.0003

Data Index: 193504 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1120. Min Act: -0.0002

Data Index: 90039 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1069. Min Act: -0.0002

Data Index: 1010634 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1101. Min Act: -0.0003

Data Index: 550797 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1097. Min Act: -0.0003

Data Index: 310382 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1098. Min Act: -0.0003

Data Index: 1016087 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1051. Min Act: -0.0003

Data Index: 470446 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1063. Min Act: -0.0003

Data Index: 91012 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1055. Min Act: -0.0003

Data Index: 1228533 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1055. Min Act: -0.0003

Data Index: 158258 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1050. Min Act: -0.0003

Data Index: 1157016 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1082. Min Act: -0.0003

Data Index: 457493 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1002. Min Act: -0.0003

Data Index: 285536 (C4 (Web Text))

Max Activating Token Index: 239