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

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

Neuron 2769 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1133906 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1103999 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1275135 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1216. Min Act: -0.0001

Data Index: 33658 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1217. Min Act: -0.0001

Data Index: 763476 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1265. Min Act: -0.0001

Data Index: 472279 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1195. Min Act: -0.0001

Data Index: 609503 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1192. Min Act: -0.0001

Data Index: 92928 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1143. Min Act: -0.0001

Data Index: 443423 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1178. Min Act: -0.0001

Data Index: 152165 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1210. Min Act: -0.0001

Data Index: 522590 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1158. Min Act: -0.0001

Data Index: 508379 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1141. Min Act: -0.0001

Data Index: 99177 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1120. Min Act: -0.0001

Data Index: 503528 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1103. Min Act: -0.0001

Data Index: 397030 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1063. Min Act: -0.0001

Data Index: 557484 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1074. Min Act: -0.0001

Data Index: 807555 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1108. Min Act: -0.0001

Data Index: 417571 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1282954 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1379328 (Python Code)

Max Activating Token Index: 965