Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5081 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3502. Min Act: -0.0000

Data Index: 387037 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1823131 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1679902 (The Pile)

Max Activating Token Index: 58

Text #3

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3684. Min Act: -0.0000

Data Index: 443682 (The Pile)

Max Activating Token Index: 60

Text #4

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1970747 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.4061. Min Act: -0.0000

Data Index: 850435 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3492. Min Act: -0.0000

Data Index: 826874 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1376260 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3435. Min Act: -0.0000

Data Index: 164784 (The Pile)

Max Activating Token Index: 875

Text #9

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1826514 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2984. Min Act: -0.0000

Data Index: 483545 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3213. Min Act: -0.0000

Data Index: 498953 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1795450 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1027266 (The Pile)

Max Activating Token Index: 193

Text #14

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2746. Min Act: -0.0000

Data Index: 487920 (The Pile)

Max Activating Token Index: 964

Text #15

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1105636 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3220. Min Act: -0.0000

Data Index: 845198 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1714970 (The Pile)

Max Activating Token Index: 747

Text #18

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1959213 (The Pile)

Max Activating Token Index: 922

Text #19

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1676706 (The Pile)

Max Activating Token Index: 573