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

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

Neuron 4440 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: 1.5274. Min Range: -1.5274

Max Act: 1.5274. Min Act: -0.0000

Data Index: 1177171 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.3420. Min Act: -0.0000

Data Index: 762929 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.3629. Min Act: -0.0000

Data Index: 129518 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.2215. Min Act: -0.0000

Data Index: 523552 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.2531. Min Act: -0.0000

Data Index: 187879 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.2884. Min Act: -0.0000

Data Index: 603067 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.1948. Min Act: -0.0000

Data Index: 360846 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.1813. Min Act: -0.0000

Data Index: 1282120 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.1943. Min Act: -0.0000

Data Index: 411810 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.1265. Min Act: -0.0000

Data Index: 680727 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.1193. Min Act: -0.0000

Data Index: 773829 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.1503. Min Act: -0.0000

Data Index: 276312 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.0675. Min Act: -0.0000

Data Index: 437492 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.0517. Min Act: -0.0000

Data Index: 616829 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.0513. Min Act: -0.0000

Data Index: 684077 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.0262. Min Act: -0.0000

Data Index: 812668 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 1.5274. Min Range: -1.5274

Max Act: 0.9534. Min Act: -0.0000

Data Index: 871970 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 1.5274. Min Range: -1.5274

Max Act: 0.9712. Min Act: -0.0000

Data Index: 318424 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.0043. Min Act: -0.0000

Data Index: 878129 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.0047. Min Act: -0.0000

Data Index: 1051085 (C4 (Web Text))

Max Activating Token Index: 768