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

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

Neuron 979 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: 0.1523. Min Range: -0.1523

Max Act: 0.1523. Min Act: -0.0002

Data Index: 1356636 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1296. Min Act: -0.0002

Data Index: 1413022 (Python Code)

Max Activating Token Index: 485

Text #2

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1247. Min Act: -0.0002

Data Index: 792023 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1266. Min Act: -0.0002

Data Index: 363365 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1303. Min Act: -0.0002

Data Index: 451267 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1287. Min Act: -0.0002

Data Index: 11692 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1249. Min Act: -0.0002

Data Index: 764167 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1030766 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1220. Min Act: -0.0002

Data Index: 1550822 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1228. Min Act: -0.0002

Data Index: 576034 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1157. Min Act: -0.0002

Data Index: 220279 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1160. Min Act: -0.0002

Data Index: 723948 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1143. Min Act: -0.0002

Data Index: 165432 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1181. Min Act: -0.0002

Data Index: 257702 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1077. Min Act: -0.0002

Data Index: 257087 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1154. Min Act: -0.0002

Data Index: 223887 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1120. Min Act: -0.0002

Data Index: 1505240 (Python Code)

Max Activating Token Index: 265

Text #17

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1118. Min Act: -0.0002

Data Index: 496149 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1054. Min Act: -0.0002

Data Index: 998064 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.1523. Min Range: -0.1523

Max Act: 0.1123. Min Act: 0.0003

Data Index: 1335807 (C4 (Web Text))

Max Activating Token Index: 643