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

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

Neuron 1996 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.9178. Min Act: -0.0000

Data Index: 699906 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.7632. Min Act: -0.0000

Data Index: 1089519 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.4892. Min Act: -0.0000

Data Index: 1336653 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.5425. Min Act: -0.0000

Data Index: 305343 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.5196. Min Act: -0.0000

Data Index: 108213 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.3685. Min Act: -0.0000

Data Index: 157633 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.4806. Min Act: -0.0000

Data Index: 1006283 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.4676. Min Act: -0.0000

Data Index: 420820 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.4509. Min Act: -0.0000

Data Index: 265580 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.4348. Min Act: -0.0000

Data Index: 1816 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.4043. Min Act: -0.0000

Data Index: 1222123 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.3898. Min Act: -0.0000

Data Index: 788375 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.2573. Min Act: -0.0000

Data Index: 269513 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.4720. Min Act: -0.0000

Data Index: 1030659 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.2314. Min Act: -0.0000

Data Index: 970837 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.3275. Min Act: -0.0000

Data Index: 88244 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.3066. Min Act: -0.0000

Data Index: 71803 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.2956. Min Act: -0.0000

Data Index: 639157 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.4058. Min Act: -0.0000

Data Index: 997312 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 2.9178. Min Range: -2.9178

Max Act: 2.1732. Min Act: -0.0000

Data Index: 47372 (C4 (Web Text))

Max Activating Token Index: 60