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

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

Neuron 1703 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: 0.1437. Min Range: -0.1437

Max Act: 0.1437. Min Act: -0.0002

Data Index: 362254 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1214. Min Act: -0.0002

Data Index: 1193414 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1193. Min Act: -0.0002

Data Index: 331654 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1210. Min Act: -0.0002

Data Index: 1072466 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1172. Min Act: -0.0002

Data Index: 167030 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1116278 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1138. Min Act: -0.0002

Data Index: 72621 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1195. Min Act: -0.0002

Data Index: 607690 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1155. Min Act: -0.0002

Data Index: 162087 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1185. Min Act: -0.0002

Data Index: 19741 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1145. Min Act: -0.0002

Data Index: 158434 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1075. Min Act: -0.0002

Data Index: 350905 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1183. Min Act: -0.0002

Data Index: 606284 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1175. Min Act: -0.0002

Data Index: 1297616 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1074035 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1128. Min Act: -0.0002

Data Index: 1336220 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1049. Min Act: -0.0002

Data Index: 970364 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1108. Min Act: -0.0002

Data Index: 216377 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1064. Min Act: -0.0002

Data Index: 124965 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 0.1437. Min Range: -0.1437

Max Act: 0.1002. Min Act: -0.0002

Data Index: 824524 (C4 (Web Text))

Max Activating Token Index: 260