Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3598 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9597. Min Act: -0.0001

Data Index: 1288925 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 1.0788. Min Range: -1.0788

Max Act: 1.0788. Min Act: -0.0001

Data Index: 1196238 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 1.0788. Min Range: -1.0788

Max Act: 1.0300. Min Act: -0.0001

Data Index: 3311 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.9509. Min Act: -0.0001

Data Index: 501759 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8351. Min Act: -0.0001

Data Index: 1243166 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8433. Min Act: -0.0001

Data Index: 410986 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8551. Min Act: -0.0001

Data Index: 200038 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8918. Min Act: -0.0001

Data Index: 675775 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8013. Min Act: -0.0001

Data Index: 1276407 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8464. Min Act: -0.0001

Data Index: 1225431 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7117. Min Act: -0.0001

Data Index: 200850 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8396. Min Act: -0.0001

Data Index: 323403 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8637. Min Act: -0.0001

Data Index: 1021925 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7780. Min Act: -0.0001

Data Index: 199951 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.8320. Min Act: -0.0001

Data Index: 1321798 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7790. Min Act: -0.0001

Data Index: 922527 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7759. Min Act: -0.0001

Data Index: 865286 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7471. Min Act: -0.0001

Data Index: 458392 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.7752. Min Act: -0.0001

Data Index: 569280 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 1.0788. Min Range: -1.0788

Max Act: 0.6193. Min Act: -0.0001

Data Index: 671644 (C4 (Web Text))

Max Activating Token Index: 521