Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1191 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1207. Min Act: -0.0002

Data Index: 361002 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1223. Min Act: -0.0002

Data Index: 464586 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1224. Min Act: -0.0002

Data Index: 913731 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1152. Min Act: -0.0002

Data Index: 336285 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1148. Min Act: -0.0002

Data Index: 522587 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1210. Min Act: -0.0002

Data Index: 1101217 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1130. Min Act: -0.0002

Data Index: 79914 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1082. Min Act: -0.0002

Data Index: 116385 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1083730 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1073. Min Act: -0.0002

Data Index: 1180480 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1124. Min Act: -0.0002

Data Index: 825063 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1109. Min Act: -0.0002

Data Index: 780871 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1061458 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1052. Min Act: -0.0002

Data Index: 178349 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1072. Min Act: -0.0002

Data Index: 516634 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1028. Min Act: -0.0002

Data Index: 365811 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1044. Min Act: -0.0002

Data Index: 843253 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1326088 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1000. Min Act: -0.0002

Data Index: 201544 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0998. Min Act: -0.0002

Data Index: 1280638 (C4 (Web Text))

Max Activating Token Index: 365