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

Dataset: The Pile

Neuron 2312 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.2741. Min Act: -0.0000

Data Index: 1939401 (The Pile)

Max Activating Token Index: 834

Text #1

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.2271. Min Act: -0.0000

Data Index: 561841 (The Pile)

Max Activating Token Index: 48

Text #2

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.1856. Min Act: -0.0000

Data Index: 599302 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.3471. Min Act: -0.0000

Data Index: 490766 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.1150. Min Act: -0.0000

Data Index: 703759 (The Pile)

Max Activating Token Index: 23

Text #5

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0640. Min Act: -0.0000

Data Index: 542058 (The Pile)

Max Activating Token Index: 16

Text #6

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.1096. Min Act: -0.0000

Data Index: 696163 (The Pile)

Max Activating Token Index: 34

Text #7

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0265. Min Act: -0.0000

Data Index: 639612 (The Pile)

Max Activating Token Index: 12

Text #8

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0876. Min Act: -0.0000

Data Index: 1025073 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.1198. Min Act: -0.0000

Data Index: 614430 (The Pile)

Max Activating Token Index: 9

Text #10

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1599204 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0961. Min Act: -0.0000

Data Index: 40595 (The Pile)

Max Activating Token Index: 926

Text #12

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0271. Min Act: -0.0000

Data Index: 592526 (The Pile)

Max Activating Token Index: 13

Text #13

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0506. Min Act: -0.0000

Data Index: 1737929 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0448. Min Act: -0.0000

Data Index: 680355 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0391. Min Act: -0.0000

Data Index: 366107 (The Pile)

Max Activating Token Index: 15

Text #16

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1994270 (The Pile)

Max Activating Token Index: 774

Text #17

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0628. Min Act: -0.0000

Data Index: 726980 (The Pile)

Max Activating Token Index: 14

Text #18

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0270. Min Act: -0.0000

Data Index: 448798 (The Pile)

Max Activating Token Index: 107

Text #19

Max Range: 1.3471. Min Range: -1.3471

Max Act: 1.0221. Min Act: -0.0000

Data Index: 395612 (The Pile)

Max Activating Token Index: 130