Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4161 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.2953. Min Act: -0.0000

Data Index: 1212774 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.1702. Min Act: -0.0000

Data Index: 694000 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.1764. Min Act: -0.0000

Data Index: 1186492 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.1526. Min Act: -0.0000

Data Index: 810286 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.1509. Min Act: -0.0000

Data Index: 856029 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0046. Min Act: -0.0000

Data Index: 298868 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1043895 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.2061. Min Act: 0.0000

Data Index: 339049 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.1083. Min Act: -0.0000

Data Index: 853599 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1282564 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0347. Min Act: -0.0000

Data Index: 665188 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 1.2953. Min Range: -1.2953

Max Act: 0.9725. Min Act: -0.0000

Data Index: 808413 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.1045. Min Act: -0.0000

Data Index: 1276435 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 1.2953. Min Range: -1.2953

Max Act: 1.0069. Min Act: -0.0000

Data Index: 629769 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.2953. Min Range: -1.2953

Max Act: 0.9388. Min Act: -0.0000

Data Index: 1114891 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 1.2953. Min Range: -1.2953

Max Act: 0.9961. Min Act: -0.0000

Data Index: 670013 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 1.2953. Min Range: -1.2953

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1265603 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 1.2953. Min Range: -1.2953

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1163558 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 1.2953. Min Range: -1.2953

Max Act: 0.9787. Min Act: -0.0000

Data Index: 429761 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 1.2953. Min Range: -1.2953

Max Act: 0.9181. Min Act: -0.0000

Data Index: 128397 (C4 (Web Text))

Max Activating Token Index: 273