Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1395 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1682. Min Act: -0.0000

Data Index: 808121 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1373. Min Act: -0.0001

Data Index: 152777 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1366. Min Act: -0.0001

Data Index: 265077 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1387. Min Act: -0.0001

Data Index: 1333344 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1073989 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1238. Min Act: -0.0000

Data Index: 766267 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1243. Min Act: -0.0001

Data Index: 280207 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1101562 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1162639 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1157. Min Act: -0.0000

Data Index: 686819 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1191. Min Act: -0.0000

Data Index: 498191 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1139. Min Act: -0.0000

Data Index: 316513 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1129. Min Act: -0.0000

Data Index: 999306 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1166. Min Act: -0.0001

Data Index: 403816 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1084. Min Act: -0.0000

Data Index: 213317 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1160. Min Act: -0.0000

Data Index: 341993 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1199514 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.0992. Min Act: -0.0000

Data Index: 919002 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1138023 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1154932 (C4 (Web Text))

Max Activating Token Index: 198