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

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

Neuron 4419 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.7495. Min Act: -0.0000

Data Index: 478894 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.7066. Min Act: -0.0000

Data Index: 463940 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.7142. Min Act: -0.0000

Data Index: 954557 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6677. Min Act: -0.0000

Data Index: 684435 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6516. Min Act: -0.0000

Data Index: 556063 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6673. Min Act: -0.0000

Data Index: 740019 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6474. Min Act: -0.0000

Data Index: 643101 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6142. Min Act: -0.0000

Data Index: 320983 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6598. Min Act: 0.0000

Data Index: 852726 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6330. Min Act: -0.0000

Data Index: 704181 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6746. Min Act: -0.0000

Data Index: 420041 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1221555 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6246. Min Act: 0.0000

Data Index: 187428 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6304. Min Act: -0.0000

Data Index: 374587 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5795. Min Act: -0.0000

Data Index: 94185 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6260. Min Act: 0.0000

Data Index: 89918 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5864. Min Act: -0.0000

Data Index: 917597 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6078. Min Act: -0.0000

Data Index: 659874 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6035. Min Act: -0.0000

Data Index: 509332 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1350465 (C4 (Web Text))

Max Activating Token Index: 731