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

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

Neuron 1068 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.1962. Min Act: -0.0000

Data Index: 602013 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.1210. Min Act: -0.0000

Data Index: 815700 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9432. Min Act: -0.0000

Data Index: 1072269 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9365. Min Act: 0.0001

Data Index: 687224 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1150704 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1101620 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9134. Min Act: -0.0000

Data Index: 927969 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8719. Min Act: -0.0000

Data Index: 294552 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8759. Min Act: -0.0000

Data Index: 432229 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8308. Min Act: -0.0000

Data Index: 762141 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8812. Min Act: -0.0000

Data Index: 745544 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8359. Min Act: -0.0000

Data Index: 548299 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8397. Min Act: -0.0000

Data Index: 384411 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8327. Min Act: -0.0000

Data Index: 973072 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8262. Min Act: -0.0000

Data Index: 881647 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8028. Min Act: -0.0000

Data Index: 762950 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1144054 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8129. Min Act: -0.0000

Data Index: 361846 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8113. Min Act: -0.0000

Data Index: 818268 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8061. Min Act: -0.0000

Data Index: 445715 (C4 (Web Text))

Max Activating Token Index: 123