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

Dataset: The Pile

Neuron 4343 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0277. Min Act: 0.0000

Data Index: 147224 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0263. Min Act: 0.0000

Data Index: 286288 (The Pile)

Max Activating Token Index: 2

Text #2

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0251. Min Act: 0.0000

Data Index: 1903137 (The Pile)

Max Activating Token Index: 5

Text #3

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0263. Min Act: 0.0000

Data Index: 1052480 (The Pile)

Max Activating Token Index: 2

Text #4

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0263. Min Act: 0.0000

Data Index: 263058 (The Pile)

Max Activating Token Index: 2

Text #5

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1797410 (The Pile)

Max Activating Token Index: 2

Text #6

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0254. Min Act: 0.0000

Data Index: 1038081 (The Pile)

Max Activating Token Index: 2

Text #7

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0252. Min Act: -0.0000

Data Index: 1636686 (The Pile)

Max Activating Token Index: 3

Text #8

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0250. Min Act: 0.0000

Data Index: 678951 (The Pile)

Max Activating Token Index: 2

Text #9

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0244. Min Act: 0.0000

Data Index: 1809599 (The Pile)

Max Activating Token Index: 3

Text #10

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0243. Min Act: 0.0000

Data Index: 769741 (The Pile)

Max Activating Token Index: 2

Text #11

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0242. Min Act: 0.0000

Data Index: 13987 (The Pile)

Max Activating Token Index: 2

Text #12

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0241. Min Act: -0.0000

Data Index: 284059 (The Pile)

Max Activating Token Index: 2

Text #13

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0237. Min Act: 0.0000

Data Index: 771374 (The Pile)

Max Activating Token Index: 2

Text #14

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0237. Min Act: 0.0000

Data Index: 603042 (The Pile)

Max Activating Token Index: 2

Text #15

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0237. Min Act: -0.0000

Data Index: 257345 (The Pile)

Max Activating Token Index: 3

Text #16

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0235. Min Act: 0.0000

Data Index: 864882 (The Pile)

Max Activating Token Index: 3

Text #17

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0231. Min Act: 0.0000

Data Index: 405773 (The Pile)

Max Activating Token Index: 2

Text #18

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0231. Min Act: -0.0000

Data Index: 1876130 (The Pile)

Max Activating Token Index: 2

Text #19

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0228. Min Act: 0.0000

Data Index: 948181 (The Pile)

Max Activating Token Index: 3