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

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

Neuron 3300 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: 0.1257. Min Range: -0.1257

Max Act: 0.1257. Min Act: -0.0001

Data Index: 610527 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1195. Min Act: -0.0000

Data Index: 682807 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1177. Min Act: -0.0001

Data Index: 1122632 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1059383 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1070. Min Act: -0.0001

Data Index: 946375 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1124980 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1150. Min Act: -0.0001

Data Index: 232006 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1034376 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1001611 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0993. Min Act: -0.0001

Data Index: 861656 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1029. Min Act: -0.0001

Data Index: 59938 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1156311 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1043. Min Act: -0.0001

Data Index: 269433 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1040. Min Act: -0.0001

Data Index: 512758 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1081. Min Act: -0.0001

Data Index: 832499 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1041. Min Act: -0.0001

Data Index: 475420 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0966. Min Act: -0.0000

Data Index: 31265 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1119671 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1019. Min Act: -0.0001

Data Index: 351829 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1128220 (C4 (Web Text))

Max Activating Token Index: 515