Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3302 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1221. Min Act: -0.0000

Data Index: 700310 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1149297 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1183. Min Act: -0.0000

Data Index: 965810 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1263. Min Act: -0.0000

Data Index: 453549 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1156. Min Act: -0.0000

Data Index: 299940 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1194886 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1122. Min Act: -0.0000

Data Index: 821443 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1159394 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1119. Min Act: -0.0000

Data Index: 18566 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1037. Min Act: -0.0000

Data Index: 597049 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1320450 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1097. Min Act: -0.0000

Data Index: 324922 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1342809 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1087. Min Act: -0.0000

Data Index: 807853 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1066. Min Act: -0.0000

Data Index: 537225 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1118. Min Act: -0.0000

Data Index: 340819 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1035. Min Act: -0.0000

Data Index: 750371 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0999. Min Act: -0.0000

Data Index: 936690 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0996. Min Act: -0.0000

Data Index: 840556 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1069. Min Act: -0.0000

Data Index: 795112 (C4 (Web Text))

Max Activating Token Index: 494