Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2471 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0725. Min Range: -1.0725

Max Act: 1.0725. Min Act: 0.0000

Data Index: 490462 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.9308. Min Act: 0.0001

Data Index: 579189 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.9360. Min Act: 0.0001

Data Index: 1196297 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.8976. Min Act: -0.0000

Data Index: 237845 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.8806. Min Act: 0.0001

Data Index: 1316370 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.8561. Min Act: 0.0000

Data Index: 394404 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.7842. Min Act: 0.0001

Data Index: 941052 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.8121. Min Act: 0.0001

Data Index: 1010739 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.7628. Min Act: 0.0000

Data Index: 902502 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.7916. Min Act: 0.0001

Data Index: 529137 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.8240. Min Act: 0.0001

Data Index: 34627 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1273162 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.8108. Min Act: 0.0001

Data Index: 302455 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.7491. Min Act: 0.0001

Data Index: 254938 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.7453. Min Act: 0.0001

Data Index: 1085593 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.7124. Min Act: 0.0000

Data Index: 658270 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.7062. Min Act: 0.0001

Data Index: 516490 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.7215. Min Act: 0.0000

Data Index: 1152058 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.7466. Min Act: 0.0000

Data Index: 89041 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 1.0725. Min Range: -1.0725

Max Act: 0.7027. Min Act: 0.0001

Data Index: 319090 (C4 (Web Text))

Max Activating Token Index: 292