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

Dataset: The Pile

Neuron 2540 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2173. Min Range: -1.2173

Max Act: 1.1737. Min Act: -0.0000

Data Index: 172806 (The Pile)

Max Activating Token Index: 853

Text #1

Max Range: 1.2173. Min Range: -1.2173

Max Act: 1.2173. Min Act: -0.0000

Data Index: 668391 (The Pile)

Max Activating Token Index: 226

Text #2

Max Range: 1.2173. Min Range: -1.2173

Max Act: 1.1566. Min Act: -0.0000

Data Index: 1737037 (The Pile)

Max Activating Token Index: 891

Text #3

Max Range: 1.2173. Min Range: -1.2173

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1064432 (The Pile)

Max Activating Token Index: 47

Text #4

Max Range: 1.2173. Min Range: -1.2173

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1609366 (The Pile)

Max Activating Token Index: 381

Text #5

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9330. Min Act: -0.0000

Data Index: 478485 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9190. Min Act: -0.0000

Data Index: 1372441 (The Pile)

Max Activating Token Index: 385

Text #7

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9193. Min Act: -0.0000

Data Index: 378145 (The Pile)

Max Activating Token Index: 762

Text #8

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9062. Min Act: -0.0000

Data Index: 823040 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9529. Min Act: -0.0000

Data Index: 207962 (The Pile)

Max Activating Token Index: 713

Text #10

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1652675 (The Pile)

Max Activating Token Index: 790

Text #11

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9313. Min Act: -0.0000

Data Index: 201627 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8953. Min Act: 0.0000

Data Index: 658318 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1930470 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9186. Min Act: -0.0000

Data Index: 945299 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8908. Min Act: -0.0000

Data Index: 696237 (The Pile)

Max Activating Token Index: 282

Text #16

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1040128 (The Pile)

Max Activating Token Index: 69

Text #17

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1940462 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1177970 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9939. Min Act: -0.0000

Data Index: 711389 (The Pile)

Max Activating Token Index: 592