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

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

Neuron 5187 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.8362. Min Act: -0.0000

Data Index: 941542 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.7289. Min Act: -0.0000

Data Index: 353730 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.7499. Min Act: -0.0000

Data Index: 873759 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.7417. Min Act: -0.0000

Data Index: 569904 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1042353 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1075987 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.6085. Min Act: -0.0000

Data Index: 566341 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.6246. Min Act: -0.0000

Data Index: 466929 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.6246. Min Act: -0.0000

Data Index: 532622 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.6312. Min Act: -0.0000

Data Index: 574757 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5808. Min Act: -0.0000

Data Index: 955888 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1034615 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5842. Min Act: -0.0000

Data Index: 825150 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5870. Min Act: -0.0000

Data Index: 791624 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5609. Min Act: -0.0000

Data Index: 450071 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.6088. Min Act: -0.0000

Data Index: 609864 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5020. Min Act: -0.0000

Data Index: 291352 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1052796 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.4998. Min Act: -0.0000

Data Index: 972101 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.4232. Min Act: -0.0000

Data Index: 618411 (C4 (Web Text))

Max Activating Token Index: 313