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

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

Neuron 939 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0057. Min Act: -0.0002

Data Index: 765078 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0045. Min Act: -0.0002

Data Index: 914304 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0044. Min Act: -0.0002

Data Index: 590200 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0044. Min Act: -0.0003

Data Index: 89090 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1349673 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1090329 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0041. Min Act: -0.0002

Data Index: 924994 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0041. Min Act: -0.0003

Data Index: 478263 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0041. Min Act: -0.0003

Data Index: 160210 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0041. Min Act: -0.0002

Data Index: 34055 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0041. Min Act: -0.0002

Data Index: 1278155 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1295 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0040. Min Act: -0.0003

Data Index: 352873 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0038. Min Act: -0.0002

Data Index: 657315 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0037. Min Act: -0.0002

Data Index: 694853 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1109211 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0037. Min Act: -0.0002

Data Index: 607848 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1014021 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1177903 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0036. Min Act: -0.0003

Data Index: 873375 (C4 (Web Text))

Max Activating Token Index: 805