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

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

Neuron 586 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: 0.0824. Min Range: -0.0824

Max Act: 0.0824. Min Act: -0.0003

Data Index: 1091933 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0512. Min Act: -0.0003

Data Index: 54870 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0487. Min Act: -0.0003

Data Index: 679797 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0483. Min Act: -0.0003

Data Index: 592018 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0444. Min Act: -0.0003

Data Index: 606536 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0444. Min Act: -0.0002

Data Index: 567611 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1172998 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0421. Min Act: -0.0003

Data Index: 865007 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0422. Min Act: -0.0002

Data Index: 399721 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1192991 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0398. Min Act: -0.0003

Data Index: 970960 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0404. Min Act: -0.0003

Data Index: 92587 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1276345 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0386. Min Act: -0.0003

Data Index: 889489 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1231336 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0379. Min Act: -0.0002

Data Index: 575472 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1135874 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0373. Min Act: -0.0002

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1045114 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0359. Min Act: -0.0003

Data Index: 760348 (C4 (Web Text))

Max Activating Token Index: 809