Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3883 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4895. Min Range: -2.4895

Max Act: 2.4895. Min Act: -0.0000

Data Index: 1116492 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 2.4895. Min Range: -2.4895

Max Act: 2.3127. Min Act: -0.0000

Data Index: 227466 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 2.4895. Min Range: -2.4895

Max Act: 2.1351. Min Act: -0.0000

Data Index: 1150089 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 2.4895. Min Range: -2.4895

Max Act: 2.2425. Min Act: -0.0000

Data Index: 1306196 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 2.4895. Min Range: -2.4895

Max Act: 2.2631. Min Act: -0.0000

Data Index: 456162 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 2.4895. Min Range: -2.4895

Max Act: 2.0297. Min Act: -0.0000

Data Index: 871759 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 2.4895. Min Range: -2.4895

Max Act: 2.1302. Min Act: -0.0000

Data Index: 142247 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 2.4895. Min Range: -2.4895

Max Act: 2.0112. Min Act: -0.0000

Data Index: 199256 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 2.4895. Min Range: -2.4895

Max Act: 2.0889. Min Act: -0.0000

Data Index: 183018 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 2.4895. Min Range: -2.4895

Max Act: 1.9810. Min Act: -0.0000

Data Index: 315001 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 2.4895. Min Range: -2.4895

Max Act: 2.0330. Min Act: -0.0000

Data Index: 920997 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 2.4895. Min Range: -2.4895

Max Act: 2.0272. Min Act: -0.0000

Data Index: 295179 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 2.4895. Min Range: -2.4895

Max Act: 1.9805. Min Act: -0.0000

Data Index: 1301994 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 2.4895. Min Range: -2.4895

Max Act: 1.8716. Min Act: -0.0000

Data Index: 723520 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 2.4895. Min Range: -2.4895

Max Act: 1.8608. Min Act: -0.0000

Data Index: 48165 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 2.4895. Min Range: -2.4895

Max Act: 1.8532. Min Act: -0.0000

Data Index: 1001670 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 2.4895. Min Range: -2.4895

Max Act: 1.8284. Min Act: -0.0000

Data Index: 130173 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 2.4895. Min Range: -2.4895

Max Act: 1.7421. Min Act: -0.0000

Data Index: 915764 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 2.4895. Min Range: -2.4895

Max Act: 1.6739. Min Act: -0.0000

Data Index: 1275574 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 2.4895. Min Range: -2.4895

Max Act: 1.6323. Min Act: -0.0000

Data Index: 841351 (C4 (Web Text))

Max Activating Token Index: 147