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

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

Neuron 835 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.4169. Min Act: -0.0000

Data Index: 283358 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3719. Min Act: -0.0000

Data Index: 634992 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3076. Min Act: -0.0000

Data Index: 924153 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2963. Min Act: -0.0000

Data Index: 207901 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1043608 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1057529 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1617045 (Python Code)

Max Activating Token Index: 682

Text #7

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2727. Min Act: -0.0000

Data Index: 37727 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2794. Min Act: -0.0000

Data Index: 815694 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2473. Min Act: -0.0000

Data Index: 759699 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2548. Min Act: -0.0000

Data Index: 48100 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2674. Min Act: -0.0000

Data Index: 247080 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2284. Min Act: -0.0000

Data Index: 936770 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2172. Min Act: -0.0000

Data Index: 682657 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2439. Min Act: -0.0000

Data Index: 331640 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2300. Min Act: -0.0000

Data Index: 1355184 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2047. Min Act: -0.0000

Data Index: 750808 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1333262 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2439. Min Act: -0.0000

Data Index: 510895 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.4169. Min Range: -0.4169

Max Act: 0.2230. Min Act: -0.0000

Data Index: 622360 (C4 (Web Text))

Max Activating Token Index: 347