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

Dataset: The Pile

Neuron 2376 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1877627 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.5700. Min Act: -0.0000

Data Index: 600335 (The Pile)

Max Activating Token Index: 244

Text #2

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4268. Min Act: -0.0000

Data Index: 404209 (The Pile)

Max Activating Token Index: 673

Text #3

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4392. Min Act: -0.0000

Data Index: 111823 (The Pile)

Max Activating Token Index: 948

Text #4

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1305218 (The Pile)

Max Activating Token Index: 194

Text #5

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1312370 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4299. Min Act: -0.0000

Data Index: 858612 (The Pile)

Max Activating Token Index: 277

Text #7

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1881275 (The Pile)

Max Activating Token Index: 674

Text #8

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3776. Min Act: 0.0000

Data Index: 696708 (The Pile)

Max Activating Token Index: 709

Text #9

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1189277 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3887. Min Act: -0.0000

Data Index: 73871 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3978. Min Act: -0.0000

Data Index: 955680 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3811. Min Act: -0.0000

Data Index: 990432 (The Pile)

Max Activating Token Index: 398

Text #13

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1643645 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3900. Min Act: -0.0001

Data Index: 570876 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3521. Min Act: -0.0000

Data Index: 124782 (The Pile)

Max Activating Token Index: 658

Text #16

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1296278 (The Pile)

Max Activating Token Index: 87

Text #17

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1226484 (The Pile)

Max Activating Token Index: 389

Text #18

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1267070 (The Pile)

Max Activating Token Index: 84

Text #19

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1646792 (The Pile)

Max Activating Token Index: 903