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

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

Neuron 4372 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1060. Min Act: -0.0000

Data Index: 301245 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1110. Min Act: -0.0000

Data Index: 396323 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1088. Min Act: -0.0000

Data Index: 662385 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1298212 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0943. Min Act: -0.0000

Data Index: 864468 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0876. Min Act: -0.0000

Data Index: 836063 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0921. Min Act: -0.0000

Data Index: 44443 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0922. Min Act: -0.0000

Data Index: 804370 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1207701 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0815. Min Act: -0.0000

Data Index: 39922 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1214334 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0714. Min Act: -0.0000

Data Index: 893963 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0859. Min Act: -0.0000

Data Index: 160327 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0877. Min Act: -0.0000

Data Index: 73738 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1080533 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0824. Min Act: 0.0000

Data Index: 1199206 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0824. Min Act: -0.0000

Data Index: 588994 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0827. Min Act: -0.0000

Data Index: 506380 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0831. Min Act: -0.0001

Data Index: 199268 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0786. Min Act: -0.0000

Data Index: 582281 (C4 (Web Text))

Max Activating Token Index: 54