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

Dataset: The Pile

Neuron 3845 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1256653 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1702238 (The Pile)

Max Activating Token Index: 576

Text #2

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6202. Min Act: -0.0000

Data Index: 637594 (The Pile)

Max Activating Token Index: 230

Text #3

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1300914 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5874. Min Act: -0.0000

Data Index: 570156 (The Pile)

Max Activating Token Index: 912

Text #5

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1625828 (The Pile)

Max Activating Token Index: 450

Text #6

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1605209 (The Pile)

Max Activating Token Index: 437

Text #7

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1524465 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1193906 (The Pile)

Max Activating Token Index: 595

Text #9

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1360813 (The Pile)

Max Activating Token Index: 724

Text #10

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6299. Min Act: -0.0000

Data Index: 878407 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5985. Min Act: -0.0000

Data Index: 578149 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1279986 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6196. Min Act: -0.0000

Data Index: 399962 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1391028 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5986. Min Act: -0.0000

Data Index: 508053 (The Pile)

Max Activating Token Index: 585

Text #16

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1690925 (The Pile)

Max Activating Token Index: 153

Text #17

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5927. Min Act: -0.0000

Data Index: 638101 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1334869 (The Pile)

Max Activating Token Index: 585

Text #19

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1249817 (The Pile)

Max Activating Token Index: 1003