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

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

Neuron 1291 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1285. Min Act: -0.0001

Data Index: 96046 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1391. Min Act: -0.0001

Data Index: 489032 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1312. Min Act: -0.0001

Data Index: 221400 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1047779 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1295. Min Act: -0.0001

Data Index: 406017 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1186. Min Act: -0.0001

Data Index: 685807 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1183. Min Act: -0.0000

Data Index: 430062 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1226. Min Act: -0.0001

Data Index: 590739 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1168. Min Act: -0.0001

Data Index: 588431 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1123. Min Act: -0.0001

Data Index: 914934 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1259244 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1195. Min Act: -0.0000

Data Index: 839639 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1187391 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1200192 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1111. Min Act: -0.0001

Data Index: 762276 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1328381 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1114637 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1133. Min Act: -0.0001

Data Index: 308485 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1123. Min Act: -0.0001

Data Index: 353554 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.1391. Min Range: -0.1391

Max Act: 0.1122. Min Act: -0.0001

Data Index: 525703 (C4 (Web Text))

Max Activating Token Index: 825