Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 95 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6196. Min Act: -0.0003

Data Index: 65843 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6637. Min Act: -0.0003

Data Index: 191464 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6419. Min Act: -0.0003

Data Index: 452986 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5926. Min Act: -0.0003

Data Index: 318586 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5759. Min Act: -0.0003

Data Index: 588979 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6127. Min Act: -0.0003

Data Index: 155720 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5637. Min Act: -0.0003

Data Index: 755604 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5826. Min Act: -0.0003

Data Index: 738090 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5821. Min Act: -0.0003

Data Index: 126822 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5695. Min Act: -0.0003

Data Index: 1357207 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5229. Min Act: -0.0003

Data Index: 537937 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5870. Min Act: -0.0003

Data Index: 421861 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6182. Min Act: -0.0003

Data Index: 127926 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5635. Min Act: -0.0003

Data Index: 1197477 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6049. Min Act: -0.0003

Data Index: 1032344 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5283. Min Act: -0.0003

Data Index: 901181 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5428. Min Act: -0.0003

Data Index: 864372 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5700. Min Act: -0.0003

Data Index: 271178 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5019. Min Act: -0.0003

Data Index: 1226736 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5523. Min Act: -0.0003

Data Index: 32850 (C4 (Web Text))

Max Activating Token Index: 917