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

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

Neuron 2199 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1310442 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1260186 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1214. Min Act: -0.0001

Data Index: 435647 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1175. Min Act: -0.0001

Data Index: 596471 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1263. Min Act: -0.0001

Data Index: 361122 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1175. Min Act: -0.0001

Data Index: 144663 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1303. Min Act: -0.0001

Data Index: 9383 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1163. Min Act: -0.0001

Data Index: 757111 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1505770 (Python Code)

Max Activating Token Index: 346

Text #9

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1110. Min Act: -0.0001

Data Index: 26991 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1149. Min Act: -0.0001

Data Index: 252995 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1158. Min Act: -0.0001

Data Index: 229537 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1125. Min Act: -0.0001

Data Index: 529869 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1125. Min Act: -0.0001

Data Index: 485069 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1123. Min Act: -0.0001

Data Index: 954635 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1122. Min Act: -0.0001

Data Index: 448404 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1034. Min Act: -0.0001

Data Index: 949142 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1069. Min Act: -0.0001

Data Index: 236307 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1082. Min Act: -0.0001

Data Index: 487048 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1087. Min Act: -0.0001

Data Index: 564337 (C4 (Web Text))

Max Activating Token Index: 597