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

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

Neuron 2441 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1199. Min Range: -1.1199

Max Act: 1.1199. Min Act: -0.0000

Data Index: 723097 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 1.1199. Min Range: -1.1199

Max Act: 1.0679. Min Act: -0.0000

Data Index: 481138 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 1.1199. Min Range: -1.1199

Max Act: 1.0353. Min Act: -0.0000

Data Index: 156145 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 1.1199. Min Range: -1.1199

Max Act: 1.0211. Min Act: -0.0000

Data Index: 855791 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.1199. Min Range: -1.1199

Max Act: 1.0208. Min Act: -0.0000

Data Index: 362408 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 1.1199. Min Range: -1.1199

Max Act: 1.0196. Min Act: -0.0000

Data Index: 839669 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.9567. Min Act: -0.0000

Data Index: 459514 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.9388. Min Act: 0.0000

Data Index: 243822 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1025076 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1006803 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.9738. Min Act: -0.0000

Data Index: 636895 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.9404. Min Act: 0.0000

Data Index: 1356200 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.9599. Min Act: -0.0000

Data Index: 765777 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.9295. Min Act: -0.0000

Data Index: 673810 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.9088. Min Act: -0.0000

Data Index: 630347 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.9378. Min Act: -0.0000

Data Index: 883567 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.8979. Min Act: -0.0000

Data Index: 869598 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.8718. Min Act: -0.0000

Data Index: 502471 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1229945 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 1.1199. Min Range: -1.1199

Max Act: 0.8875. Min Act: -0.0000

Data Index: 121718 (C4 (Web Text))

Max Activating Token Index: 277