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

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

Neuron 2104 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: 0.5592. Min Range: -0.5592

Max Act: 0.5592. Min Act: -0.0000

Data Index: 656620 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3741. Min Act: -0.0000

Data Index: 842778 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1359114 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1295193 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3503. Min Act: -0.0000

Data Index: 176544 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3459. Min Act: -0.0000

Data Index: 18905 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3447. Min Act: -0.0000

Data Index: 950922 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3397. Min Act: -0.0000

Data Index: 716589 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3227. Min Act: -0.0000

Data Index: 394685 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3487. Min Act: -0.0000

Data Index: 36349 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3187. Min Act: -0.0000

Data Index: 618309 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3112. Min Act: -0.0000

Data Index: 558941 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1059406 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3209. Min Act: 0.0000

Data Index: 1244208 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.2963. Min Act: -0.0000

Data Index: 791595 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1057623 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3032. Min Act: -0.0000

Data Index: 48596 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1127815 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.3024. Min Act: -0.0000

Data Index: 794607 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.5592. Min Range: -0.5592

Max Act: 0.2972. Min Act: -0.0000

Data Index: 223858 (C4 (Web Text))

Max Activating Token Index: 198