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

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

Neuron 1552 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: 0.1332. Min Range: -0.1332

Max Act: 0.1332. Min Act: -0.0002

Data Index: 62524 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1199. Min Act: -0.0002

Data Index: 444565 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1191. Min Act: -0.0002

Data Index: 889106 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1136. Min Act: -0.0002

Data Index: 1353811 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1082. Min Act: -0.0002

Data Index: 498993 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1157. Min Act: -0.0002

Data Index: 451131 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1121. Min Act: -0.0002

Data Index: 835059 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1156. Min Act: -0.0002

Data Index: 218765 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1104. Min Act: -0.0002

Data Index: 541918 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1084. Min Act: -0.0002

Data Index: 544623 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1199404 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1079. Min Act: -0.0002

Data Index: 1147380 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1039. Min Act: -0.0002

Data Index: 1225082 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1045. Min Act: -0.0002

Data Index: 1154454 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1072. Min Act: -0.0002

Data Index: 1270520 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1094. Min Act: -0.0002

Data Index: 160991 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1024. Min Act: -0.0002

Data Index: 797186 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1011. Min Act: -0.0002

Data Index: 119396 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1089. Min Act: -0.0002

Data Index: 282230 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1047. Min Act: -0.0002

Data Index: 927528 (C4 (Web Text))

Max Activating Token Index: 557