Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2798 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.7665. Min Act: -0.0001

Data Index: 150128 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.7205. Min Act: -0.0001

Data Index: 1031030 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6783. Min Act: -0.0001

Data Index: 878719 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.7009. Min Act: -0.0001

Data Index: 622005 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.7114. Min Act: -0.0000

Data Index: 757386 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6963. Min Act: -0.0001

Data Index: 229578 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6973. Min Act: -0.0001

Data Index: 158321 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6464. Min Act: -0.0001

Data Index: 889493 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6878. Min Act: -0.0001

Data Index: 451796 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6980. Min Act: -0.0001

Data Index: 580377 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1248059 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6318. Min Act: -0.0001

Data Index: 1515083 (Python Code)

Max Activating Token Index: 595

Text #12

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6837. Min Act: -0.0000

Data Index: 347496 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6867. Min Act: -0.0001

Data Index: 455134 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6592. Min Act: -0.0001

Data Index: 733664 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6610. Min Act: -0.0001

Data Index: 21789 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6582. Min Act: -0.0000

Data Index: 226306 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1089035 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6599. Min Act: -0.0001

Data Index: 770285 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6511. Min Act: -0.0001

Data Index: 145954 (C4 (Web Text))

Max Activating Token Index: 165