Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1211 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3496. Min Act: -0.0002

Data Index: 576870 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1133677 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1308863 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1042411 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0535. Min Act: -0.0002

Data Index: 538932 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0451. Min Act: -0.0002

Data Index: 255846 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0418. Min Act: -0.0002

Data Index: 650755 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0600. Min Act: -0.0002

Data Index: 581608 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0607. Min Act: -0.0002

Data Index: 991126 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0232. Min Act: -0.0002

Data Index: 686651 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0357. Min Act: -0.0002

Data Index: 535891 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0395. Min Act: -0.0002

Data Index: 152226 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1355680 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0242. Min Act: -0.0002

Data Index: 415280 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0406. Min Act: -0.0002

Data Index: 26684 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0310. Min Act: -0.0002

Data Index: 318009 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0400. Min Act: -0.0002

Data Index: 967200 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0204. Min Act: -0.0002

Data Index: 173568 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1056993 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.0356. Min Act: -0.0002

Data Index: 33491 (C4 (Web Text))

Max Activating Token Index: 192