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

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

Neuron 753 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1044902 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.3090. Min Act: -0.0000

Data Index: 696552 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.2921. Min Act: -0.0000

Data Index: 800526 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.2435. Min Act: -0.0000

Data Index: 715528 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.2475. Min Act: -0.0000

Data Index: 943721 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.2262. Min Act: -0.0000

Data Index: 4649 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.2296. Min Act: -0.0000

Data Index: 449419 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.2265. Min Act: -0.0000

Data Index: 273341 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.2153. Min Act: -0.0000

Data Index: 889862 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1209193 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.2057. Min Act: 0.0000

Data Index: 242054 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.2131. Min Act: 0.0000

Data Index: 826508 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.2006. Min Act: -0.0000

Data Index: 370470 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.2069. Min Act: -0.0000

Data Index: 1196501 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.1938. Min Act: -0.0000

Data Index: 431677 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.1979. Min Act: -0.0000

Data Index: 148878 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1185111 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.1875. Min Act: -0.0000

Data Index: 877866 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.1792. Min Act: -0.0000

Data Index: 499389 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.3296. Min Range: -0.3296

Max Act: 0.1868. Min Act: -0.0000

Data Index: 1298415 (C4 (Web Text))

Max Activating Token Index: 772