Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2643 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8296. Min Range: -2.8296

Max Act: 2.8296. Min Act: -0.0000

Data Index: 972983 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 2.8296. Min Range: -2.8296

Max Act: 2.5249. Min Act: -0.0000

Data Index: 872879 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 2.8296. Min Range: -2.8296

Max Act: 2.5885. Min Act: -0.0000

Data Index: 592628 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 2.8296. Min Range: -2.8296

Max Act: 2.3818. Min Act: -0.0000

Data Index: 1303825 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 2.8296. Min Range: -2.8296

Max Act: 2.2725. Min Act: -0.0000

Data Index: 438846 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 2.8296. Min Range: -2.8296

Max Act: 2.1904. Min Act: -0.0000

Data Index: 725058 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 2.8296. Min Range: -2.8296

Max Act: 2.1671. Min Act: -0.0000

Data Index: 235923 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 2.8296. Min Range: -2.8296

Max Act: 2.0516. Min Act: -0.0000

Data Index: 283981 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 2.8296. Min Range: -2.8296

Max Act: 1.9383. Min Act: -0.0000

Data Index: 26150 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 2.8296. Min Range: -2.8296

Max Act: 2.0208. Min Act: -0.0000

Data Index: 963947 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 2.8296. Min Range: -2.8296

Max Act: 1.6908. Min Act: -0.0000

Data Index: 1260505 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 2.8296. Min Range: -2.8296

Max Act: 1.9383. Min Act: -0.0000

Data Index: 220089 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 2.8296. Min Range: -2.8296

Max Act: 1.8370. Min Act: -0.0000

Data Index: 205308 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 2.8296. Min Range: -2.8296

Max Act: 1.9256. Min Act: -0.0000

Data Index: 465138 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 2.8296. Min Range: -2.8296

Max Act: 1.9261. Min Act: -0.0000

Data Index: 329585 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 2.8296. Min Range: -2.8296

Max Act: 1.9225. Min Act: -0.0000

Data Index: 394023 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 2.8296. Min Range: -2.8296

Max Act: 1.9024. Min Act: -0.0000

Data Index: 305762 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 2.8296. Min Range: -2.8296

Max Act: 1.8919. Min Act: -0.0000

Data Index: 1348883 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 2.8296. Min Range: -2.8296

Max Act: 1.9915. Min Act: -0.0000

Data Index: 346667 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 2.8296. Min Range: -2.8296

Max Act: 1.9835. Min Act: -0.0000

Data Index: 1023557 (C4 (Web Text))

Max Activating Token Index: 899