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

Dataset: The Pile

Neuron 2178 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: 0.7253. Min Range: -0.7253

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1899017 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1815504 (The Pile)

Max Activating Token Index: 269

Text #2

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.5941. Min Act: -0.0000

Data Index: 561292 (The Pile)

Max Activating Token Index: 909

Text #3

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.6204. Min Act: -0.0000

Data Index: 162818 (The Pile)

Max Activating Token Index: 885

Text #4

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.6264. Min Act: -0.0000

Data Index: 694390 (The Pile)

Max Activating Token Index: 867

Text #5

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.6021. Min Act: -0.0000

Data Index: 748895 (The Pile)

Max Activating Token Index: 1009

Text #6

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1396856 (The Pile)

Max Activating Token Index: 585

Text #7

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1587498 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.5838. Min Act: -0.0000

Data Index: 114725 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.5269. Min Act: -0.0000

Data Index: 435010 (The Pile)

Max Activating Token Index: 973

Text #10

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.5174. Min Act: -0.0000

Data Index: 835460 (The Pile)

Max Activating Token Index: 452

Text #11

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1690794 (The Pile)

Max Activating Token Index: 809

Text #12

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1344323 (The Pile)

Max Activating Token Index: 120

Text #13

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.5042. Min Act: -0.0000

Data Index: 221677 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.5448. Min Act: -0.0000

Data Index: 895647 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.5084. Min Act: -0.0000

Data Index: 330889 (The Pile)

Max Activating Token Index: 282

Text #16

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1034755 (The Pile)

Max Activating Token Index: 768

Text #17

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.5049. Min Act: -0.0000

Data Index: 238956 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.4738. Min Act: -0.0000

Data Index: 525412 (The Pile)

Max Activating Token Index: 756

Text #19

Max Range: 0.7253. Min Range: -0.7253

Max Act: 0.4975. Min Act: -0.0000

Data Index: 713624 (The Pile)

Max Activating Token Index: 675