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

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

Neuron 201 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1354. Min Range: -1.1354

Max Act: 1.1354. Min Act: -0.0000

Data Index: 274354 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 1.1354. Min Range: -1.1354

Max Act: 1.1292. Min Act: -0.0000

Data Index: 442051 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 1.1354. Min Range: -1.1354

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1089754 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 1.1354. Min Range: -1.1354

Max Act: 1.0011. Min Act: -0.0000

Data Index: 828265 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 1.1354. Min Range: -1.1354

Max Act: 1.1210. Min Act: -0.0000

Data Index: 507550 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 1.1354. Min Range: -1.1354

Max Act: 1.0290. Min Act: -0.0000

Data Index: 231748 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 1.1354. Min Range: -1.1354

Max Act: 1.0116. Min Act: -0.0000

Data Index: 588227 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 1.1354. Min Range: -1.1354

Max Act: 1.0116. Min Act: -0.0000

Data Index: 568262 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 1.1354. Min Range: -1.1354

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1048597 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.1354. Min Range: -1.1354

Max Act: 0.9756. Min Act: -0.0000

Data Index: 942684 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 1.1354. Min Range: -1.1354

Max Act: 0.9630. Min Act: -0.0000

Data Index: 46186 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.1354. Min Range: -1.1354

Max Act: 0.9073. Min Act: -0.0000

Data Index: 746568 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 1.1354. Min Range: -1.1354

Max Act: 0.9382. Min Act: -0.0000

Data Index: 137973 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 1.1354. Min Range: -1.1354

Max Act: 1.0178. Min Act: -0.0000

Data Index: 367276 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 1.1354. Min Range: -1.1354

Max Act: 0.8970. Min Act: -0.0000

Data Index: 1076846 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 1.1354. Min Range: -1.1354

Max Act: 0.9156. Min Act: -0.0000

Data Index: 347683 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 1.1354. Min Range: -1.1354

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1279674 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 1.1354. Min Range: -1.1354

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1136276 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 1.1354. Min Range: -1.1354

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1254233 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 1.1354. Min Range: -1.1354

Max Act: 0.9605. Min Act: -0.0000

Data Index: 626803 (C4 (Web Text))

Max Activating Token Index: 80