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

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

Neuron 5795 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: 4.0026. Min Range: -4.0026

Max Act: 4.0026. Min Act: -0.0000

Data Index: 640594 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.5590. Min Act: -0.0000

Data Index: 426703 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.5364. Min Act: -0.0000

Data Index: 254590 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.5207. Min Act: -0.0000

Data Index: 87932 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.2716. Min Act: -0.0000

Data Index: 1344986 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.1958. Min Act: -0.0000

Data Index: 139461 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.0443. Min Act: -0.0000

Data Index: 451143 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.2445. Min Act: -0.0000

Data Index: 657991 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.2279. Min Act: -0.0000

Data Index: 437431 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 4.0026. Min Range: -4.0026

Max Act: 2.8773. Min Act: -0.0000

Data Index: 651663 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 4.0026. Min Range: -4.0026

Max Act: 2.9834. Min Act: -0.0000

Data Index: 469201 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.2522. Min Act: -0.0000

Data Index: 913657 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.0524. Min Act: -0.0000

Data Index: 1177815 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.3455. Min Act: -0.0000

Data Index: 1313823 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.1852. Min Act: -0.0000

Data Index: 279788 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.0392. Min Act: -0.0000

Data Index: 958945 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 4.0026. Min Range: -4.0026

Max Act: 2.8737. Min Act: -0.0000

Data Index: 491510 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 4.0026. Min Range: -4.0026

Max Act: 2.9880. Min Act: -0.0000

Data Index: 767496 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 4.0026. Min Range: -4.0026

Max Act: 2.9229. Min Act: -0.0000

Data Index: 770365 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 4.0026. Min Range: -4.0026

Max Act: 3.0805. Min Act: -0.0000

Data Index: 1279714 (C4 (Web Text))

Max Activating Token Index: 670