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

Dataset: The Pile

Neuron 2998 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: 1.4310. Min Range: -1.4310

Max Act: 1.3389. Min Act: -0.0000

Data Index: 334659 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.4310. Min Act: -0.0000

Data Index: 201806 (The Pile)

Max Activating Token Index: 48

Text #2

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.2156. Min Act: -0.0000

Data Index: 440700 (The Pile)

Max Activating Token Index: 740

Text #3

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.2510. Min Act: -0.0000

Data Index: 1347048 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.2178. Min Act: -0.0000

Data Index: 895317 (The Pile)

Max Activating Token Index: 847

Text #5

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.2230. Min Act: -0.0000

Data Index: 426152 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.2266. Min Act: -0.0000

Data Index: 1720831 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.1818. Min Act: -0.0000

Data Index: 1933256 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.1127. Min Act: -0.0000

Data Index: 1696024 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.1260. Min Act: -0.0000

Data Index: 1632238 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.0828. Min Act: -0.0000

Data Index: 1908912 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 1.4310. Min Range: -1.4310

Max Act: 0.9995. Min Act: -0.0000

Data Index: 662233 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 1.4310. Min Range: -1.4310

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1707664 (The Pile)

Max Activating Token Index: 181

Text #13

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.1090. Min Act: -0.0000

Data Index: 24818 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.0483. Min Act: -0.0000

Data Index: 341914 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.0118. Min Act: -0.0000

Data Index: 104584 (The Pile)

Max Activating Token Index: 88

Text #16

Max Range: 1.4310. Min Range: -1.4310

Max Act: 1.0536. Min Act: -0.0000

Data Index: 447276 (The Pile)

Max Activating Token Index: 234

Text #17

Max Range: 1.4310. Min Range: -1.4310

Max Act: 0.9920. Min Act: -0.0000

Data Index: 803214 (The Pile)

Max Activating Token Index: 142

Text #18

Max Range: 1.4310. Min Range: -1.4310

Max Act: 0.7634. Min Act: -0.0000

Data Index: 817117 (The Pile)

Max Activating Token Index: 973

Text #19

Max Range: 1.4310. Min Range: -1.4310

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1114378 (The Pile)

Max Activating Token Index: 198