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

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

Neuron 3232 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: 0.7270. Min Range: -0.7270

Max Act: 0.7270. Min Act: -0.0000

Data Index: 528171 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6417. Min Act: -0.0000

Data Index: 684347 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.6044. Min Act: -0.0000

Data Index: 407174 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5763. Min Act: -0.0000

Data Index: 65843 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1086491 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5632. Min Act: -0.0000

Data Index: 702363 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5885. Min Act: -0.0000

Data Index: 554656 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5297. Min Act: -0.0000

Data Index: 463266 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5408. Min Act: -0.0000

Data Index: 195279 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5326. Min Act: -0.0000

Data Index: 89031 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5297. Min Act: -0.0000

Data Index: 492578 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.4939. Min Act: -0.0000

Data Index: 401562 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5179. Min Act: -0.0000

Data Index: 250386 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5298. Min Act: -0.0000

Data Index: 129834 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.5248. Min Act: -0.0000

Data Index: 881922 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.4870. Min Act: -0.0000

Data Index: 256758 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1016556 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.4928. Min Act: -0.0000

Data Index: 808695 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.4567. Min Act: -0.0000

Data Index: 775794 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.7270. Min Range: -0.7270

Max Act: 0.4983. Min Act: -0.0000

Data Index: 912065 (C4 (Web Text))

Max Activating Token Index: 754