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

Dataset: The Pile

Neuron 660 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1811. Min Range: -3.1811

Max Act: 3.1811. Min Act: -0.0000

Data Index: 1957360 (The Pile)

Max Activating Token Index: 186

Text #1

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.5322. Min Act: -0.0000

Data Index: 1786460 (The Pile)

Max Activating Token Index: 7

Text #2

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.5535. Min Act: -0.0000

Data Index: 1872534 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.4214. Min Act: -0.0000

Data Index: 748014 (The Pile)

Max Activating Token Index: 112

Text #4

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.3837. Min Act: -0.0000

Data Index: 200610 (The Pile)

Max Activating Token Index: 72

Text #5

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.4951. Min Act: -0.0000

Data Index: 376622 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.3450. Min Act: -0.0000

Data Index: 1819891 (The Pile)

Max Activating Token Index: 377

Text #7

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.3571. Min Act: -0.0000

Data Index: 1839916 (The Pile)

Max Activating Token Index: 98

Text #8

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.1221. Min Act: -0.0000

Data Index: 98702 (The Pile)

Max Activating Token Index: 1002

Text #9

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.4310. Min Act: -0.0000

Data Index: 1337010 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.5146. Min Act: -0.0000

Data Index: 469337 (The Pile)

Max Activating Token Index: 15

Text #11

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.2616. Min Act: -0.0000

Data Index: 1579115 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.3987. Min Act: -0.0000

Data Index: 582841 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.1116. Min Act: -0.0000

Data Index: 85669 (The Pile)

Max Activating Token Index: 742

Text #14

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.2574. Min Act: -0.0000

Data Index: 431716 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.2153. Min Act: -0.0000

Data Index: 1909658 (The Pile)

Max Activating Token Index: 9

Text #16

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.0610. Min Act: -0.0000

Data Index: 138366 (The Pile)

Max Activating Token Index: 995

Text #17

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.0579. Min Act: -0.0000

Data Index: 1094875 (The Pile)

Max Activating Token Index: 877

Text #18

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.1584. Min Act: -0.0000

Data Index: 668402 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 3.1811. Min Range: -3.1811

Max Act: 2.0694. Min Act: -0.0000

Data Index: 1884354 (The Pile)

Max Activating Token Index: 10