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

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

Neuron 3679 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.1041. Min Act: -0.0000

Data Index: 614274 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.1039. Min Act: -0.0000

Data Index: 578507 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0935. Min Act: -0.0000

Data Index: 355164 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1126492 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1143796 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1321068 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0890. Min Act: -0.0000

Data Index: 484525 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0889. Min Act: -0.0000

Data Index: 154931 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.1045. Min Act: -0.0000

Data Index: 195581 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1322499 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0868. Min Act: -0.0000

Data Index: 440864 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1085384 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0923. Min Act: -0.0000

Data Index: 433750 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0750. Min Act: -0.0000

Data Index: 723529 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0693. Min Act: -0.0000

Data Index: 959532 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0868. Min Act: -0.0000

Data Index: 94422 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0664. Min Act: -0.0000

Data Index: 821476 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0782. Min Act: -0.0000

Data Index: 735155 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0648. Min Act: -0.0000

Data Index: 207506 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1340587 (C4 (Web Text))

Max Activating Token Index: 664