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

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

Neuron 1857 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: 0.1246. Min Range: -0.1246

Max Act: 0.1157. Min Act: -0.0002

Data Index: 25931 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1246. Min Act: -0.0002

Data Index: 594560 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1136. Min Act: -0.0002

Data Index: 75815 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1200. Min Act: -0.0002

Data Index: 457991 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1181. Min Act: -0.0002

Data Index: 97996 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1140. Min Act: -0.0002

Data Index: 1278754 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1168. Min Act: -0.0002

Data Index: 457035 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1130. Min Act: -0.0002

Data Index: 310268 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1138. Min Act: -0.0002

Data Index: 1311036 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1174. Min Act: -0.0002

Data Index: 192402 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1167. Min Act: -0.0002

Data Index: 449415 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1148. Min Act: -0.0002

Data Index: 220974 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1087. Min Act: -0.0002

Data Index: 196094 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1105. Min Act: -0.0002

Data Index: 996203 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1048. Min Act: -0.0002

Data Index: 86405 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1090588 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1007. Min Act: -0.0002

Data Index: 367448 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1011. Min Act: -0.0002

Data Index: 736673 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.0996. Min Act: -0.0002

Data Index: 786165 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.1246. Min Range: -0.1246

Max Act: 0.1009. Min Act: -0.0002

Data Index: 309011 (C4 (Web Text))

Max Activating Token Index: 511