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

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

Neuron 5034 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.9025. Min Act: -0.0000

Data Index: 809348 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.9339. Min Act: -0.0000

Data Index: 801545 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.8474. Min Act: -0.0000

Data Index: 113141 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5857. Min Act: -0.0000

Data Index: 189064 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6116. Min Act: -0.0000

Data Index: 365675 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6088. Min Act: -0.0000

Data Index: 496418 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6325. Min Act: -0.0000

Data Index: 37177 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6193. Min Act: -0.0000

Data Index: 429680 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6005. Min Act: -0.0000

Data Index: 725677 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5471. Min Act: -0.0000

Data Index: 744821 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6069. Min Act: -0.0000

Data Index: 940200 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6052. Min Act: -0.0000

Data Index: 635171 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5960. Min Act: -0.0000

Data Index: 328345 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5792. Min Act: -0.0000

Data Index: 771235 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5994. Min Act: -0.0000

Data Index: 966573 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1206258 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1285991 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5913. Min Act: -0.0000

Data Index: 684129 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5826. Min Act: -0.0000

Data Index: 310030 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5445. Min Act: -0.0000

Data Index: 391929 (C4 (Web Text))

Max Activating Token Index: 869