Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1054 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1263. Min Act: -0.0001

Data Index: 426026 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1231. Min Act: -0.0001

Data Index: 274924 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1177. Min Act: -0.0000

Data Index: 441732 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1164. Min Act: 0.0001

Data Index: 112477 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1160. Min Act: -0.0001

Data Index: 149220 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1098. Min Act: -0.0001

Data Index: 495681 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1098. Min Act: -0.0001

Data Index: 628176 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1170. Min Act: -0.0001

Data Index: 808413 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1130. Min Act: -0.0001

Data Index: 544511 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1125. Min Act: -0.0001

Data Index: 51715 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1319627 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1105718 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1114. Min Act: -0.0001

Data Index: 234771 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1085295 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1059. Min Act: -0.0001

Data Index: 163794 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1054. Min Act: -0.0001

Data Index: 945561 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1056981 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1086. Min Act: -0.0001

Data Index: 558113 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1079. Min Act: -0.0001

Data Index: 807111 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1080. Min Act: -0.0001

Data Index: 649682 (C4 (Web Text))

Max Activating Token Index: 870