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

Dataset: The Pile

Neuron 438 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: 3.1164. Min Range: -3.1164

Max Act: 3.1164. Min Act: -0.0000

Data Index: 27863 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.9343. Min Act: -0.0000

Data Index: 277686 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.4984. Min Act: -0.0000

Data Index: 748330 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 3.1164. Min Range: -3.1164

Max Act: 2.5507. Min Act: -0.0000

Data Index: 1464906 (The Pile)

Max Activating Token Index: 114

Text #4

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.9057. Min Act: -0.0000

Data Index: 710699 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.9589. Min Act: -0.0000

Data Index: 1648142 (The Pile)

Max Activating Token Index: 35

Text #6

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.8701. Min Act: -0.0000

Data Index: 1054134 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.7682. Min Act: -0.0000

Data Index: 1451494 (The Pile)

Max Activating Token Index: 433

Text #8

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.5953. Min Act: -0.0000

Data Index: 986610 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.4611. Min Act: -0.0000

Data Index: 1918760 (The Pile)

Max Activating Token Index: 159

Text #10

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.3207. Min Act: -0.0000

Data Index: 571359 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.6528. Min Act: -0.0000

Data Index: 1551455 (The Pile)

Max Activating Token Index: 439

Text #12

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.7054. Min Act: -0.0000

Data Index: 728572 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.6640. Min Act: -0.0000

Data Index: 1115651 (The Pile)

Max Activating Token Index: 899

Text #14

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.3559. Min Act: -0.0000

Data Index: 950860 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.8896. Min Act: -0.0000

Data Index: 362036 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.6233. Min Act: -0.0000

Data Index: 1573401 (The Pile)

Max Activating Token Index: 806

Text #17

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.4969. Min Act: -0.0000

Data Index: 145717 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1303164 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 3.1164. Min Range: -3.1164

Max Act: 1.5333. Min Act: -0.0000

Data Index: 236335 (The Pile)

Max Activating Token Index: 85