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

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

Neuron 1868 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0564. Min Range: -6.0564

Max Act: 6.0564. Min Act: -0.0000

Data Index: 1337972 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 6.0564. Min Range: -6.0564

Max Act: 3.2609. Min Act: -0.0000

Data Index: 527146 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 6.0564. Min Range: -6.0564

Max Act: 1.8760. Min Act: -0.0000

Data Index: 946936 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 6.0564. Min Range: -6.0564

Max Act: 1.1146. Min Act: -0.0000

Data Index: 380874 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 6.0564. Min Range: -6.0564

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1279814 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 6.0564. Min Range: -6.0564

Max Act: 1.1118. Min Act: -0.0000

Data Index: 408774 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 6.0564. Min Range: -6.0564

Max Act: 0.9115. Min Act: -0.0000

Data Index: 892551 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 6.0564. Min Range: -6.0564

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1035727 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 6.0564. Min Range: -6.0564

Max Act: 1.0269. Min Act: -0.0000

Data Index: 96139 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 6.0564. Min Range: -6.0564

Max Act: 0.7798. Min Act: -0.0000

Data Index: 595184 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 6.0564. Min Range: -6.0564

Max Act: 0.6353. Min Act: -0.0000

Data Index: 973282 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 6.0564. Min Range: -6.0564

Max Act: 0.8268. Min Act: -0.0000

Data Index: 892010 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 6.0564. Min Range: -6.0564

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1031953 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 6.0564. Min Range: -6.0564

Max Act: 0.8585. Min Act: -0.0000

Data Index: 929830 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 6.0564. Min Range: -6.0564

Max Act: 0.8350. Min Act: -0.0000

Data Index: 982239 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 6.0564. Min Range: -6.0564

Max Act: 0.8092. Min Act: -0.0000

Data Index: 160292 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 6.0564. Min Range: -6.0564

Max Act: 0.8226. Min Act: -0.0000

Data Index: 671248 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 6.0564. Min Range: -6.0564

Max Act: 0.8429. Min Act: -0.0000

Data Index: 818378 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 6.0564. Min Range: -6.0564

Max Act: 0.7662. Min Act: -0.0000

Data Index: 436815 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 6.0564. Min Range: -6.0564

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1078655 (C4 (Web Text))

Max Activating Token Index: 496