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

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

Neuron 651 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0037. Min Act: -0.0003

Data Index: 735467 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0032. Min Act: -0.0003

Data Index: 1171093 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0031. Min Act: -0.0003

Data Index: 581270 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0029. Min Act: -0.0003

Data Index: 29000 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0029. Min Act: -0.0002

Data Index: 246418 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0028. Min Act: -0.0003

Data Index: 969637 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0028. Min Act: -0.0003

Data Index: 292599 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0027. Min Act: -0.0002

Data Index: 1545346 (Python Code)

Max Activating Token Index: 517

Text #8

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0026. Min Act: -0.0003

Data Index: 732740 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0027. Min Act: -0.0003

Data Index: 1630524 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0027. Min Act: -0.0003

Data Index: 298012 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0026. Min Act: -0.0003

Data Index: 1627388 (Python Code)

Max Activating Token Index: 493

Text #12

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1391935 (Python Code)

Max Activating Token Index: 693

Text #13

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1413190 (Python Code)

Max Activating Token Index: 805

Text #14

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0026. Min Act: -0.0003

Data Index: 1173529 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0025. Min Act: -0.0003

Data Index: 1590727 (Python Code)

Max Activating Token Index: 751

Text #16

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1469126 (Python Code)

Max Activating Token Index: 528

Text #17

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0025. Min Act: -0.0003

Data Index: 938531 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0025. Min Act: -0.0002

Data Index: 663807 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0025. Min Act: -0.0003

Data Index: 1444407 (Python Code)

Max Activating Token Index: 501