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

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

Neuron 3612 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1256. Min Act: -0.0002

Data Index: 257412 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1435. Min Act: -0.0001

Data Index: 56036 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1183. Min Act: -0.0002

Data Index: 929279 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1239. Min Act: -0.0002

Data Index: 309782 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1024207 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1159. Min Act: -0.0002

Data Index: 1199964 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1152. Min Act: -0.0002

Data Index: 369305 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1145. Min Act: -0.0002

Data Index: 327914 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1243. Min Act: -0.0002

Data Index: 742274 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1137. Min Act: -0.0001

Data Index: 1210657 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1130. Min Act: -0.0001

Data Index: 85986 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1239. Min Act: -0.0002

Data Index: 1114623 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1308. Min Act: -0.0002

Data Index: 82187 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1063. Min Act: -0.0002

Data Index: 481379 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1251. Min Act: -0.0001

Data Index: 908251 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.0947. Min Act: -0.0002

Data Index: 160503 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1112. Min Act: -0.0002

Data Index: 1007947 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1064. Min Act: -0.0001

Data Index: 335664 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1055. Min Act: -0.0002

Data Index: 549369 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.1435. Min Range: -0.1435

Max Act: 0.1129. Min Act: -0.0002

Data Index: 741980 (C4 (Web Text))

Max Activating Token Index: 388