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

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

Neuron 1740 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.5818. Min Act: -0.0000

Data Index: 779738 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.2009. Min Act: -0.0000

Data Index: 292970 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.1906. Min Act: -0.0000

Data Index: 65042 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.1691. Min Act: -0.0000

Data Index: 617245 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0999. Min Act: -0.0000

Data Index: 66594 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.1396. Min Act: -0.0000

Data Index: 174697 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.1254. Min Act: -0.0000

Data Index: 672089 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1067898 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0198. Min Act: -0.0000

Data Index: 704031 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1352393 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 1.5818. Min Range: -1.5818

Max Act: 1.0494. Min Act: -0.0000

Data Index: 616087 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9665. Min Act: -0.0000

Data Index: 435622 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9625. Min Act: -0.0000

Data Index: 1262893 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9098. Min Act: -0.0000

Data Index: 991516 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9627. Min Act: -0.0000

Data Index: 174963 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1122396 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9317. Min Act: -0.0000

Data Index: 108142 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9321. Min Act: -0.0000

Data Index: 540637 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.9352. Min Act: -0.0000

Data Index: 370234 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 1.5818. Min Range: -1.5818

Max Act: 0.8696. Min Act: -0.0000

Data Index: 97005 (C4 (Web Text))

Max Activating Token Index: 306