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

Dataset: The Pile

Neuron 4321 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1371469 (The Pile)

Max Activating Token Index: 779

Text #1

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1709572 (The Pile)

Max Activating Token Index: 371

Text #2

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1196588 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1230573 (The Pile)

Max Activating Token Index: 1000

Text #4

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1749273 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1314503 (The Pile)

Max Activating Token Index: 184

Text #6

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6350. Min Act: -0.0000

Data Index: 759498 (The Pile)

Max Activating Token Index: 698

Text #7

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6949. Min Act: -0.0000

Data Index: 557394 (The Pile)

Max Activating Token Index: 72

Text #8

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1867650 (The Pile)

Max Activating Token Index: 320

Text #9

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6173. Min Act: -0.0000

Data Index: 203377 (The Pile)

Max Activating Token Index: 188

Text #10

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6295. Min Act: -0.0000

Data Index: 958308 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1203601 (The Pile)

Max Activating Token Index: 687

Text #12

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.6052. Min Act: -0.0000

Data Index: 886242 (The Pile)

Max Activating Token Index: 65

Text #13

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5923. Min Act: -0.0000

Data Index: 818881 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1583553 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5709. Min Act: -0.0000

Data Index: 565147 (The Pile)

Max Activating Token Index: 724

Text #16

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1886891 (The Pile)

Max Activating Token Index: 532

Text #17

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5842. Min Act: -0.0000

Data Index: 421504 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5722. Min Act: -0.0000

Data Index: 155815 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 0.7827. Min Range: -0.7827

Max Act: 0.5654. Min Act: -0.0000

Data Index: 704787 (The Pile)

Max Activating Token Index: 495