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

Dataset: The Pile

Neuron 4291 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: 1.1314. Min Range: -1.1314

Max Act: 1.1314. Min Act: -0.0000

Data Index: 932843 (The Pile)

Max Activating Token Index: 280

Text #1

Max Range: 1.1314. Min Range: -1.1314

Max Act: 1.0997. Min Act: -0.0000

Data Index: 980463 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 1.1314. Min Range: -1.1314

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1578173 (The Pile)

Max Activating Token Index: 129

Text #3

Max Range: 1.1314. Min Range: -1.1314

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1263388 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 1.1314. Min Range: -1.1314

Max Act: 1.0233. Min Act: -0.0000

Data Index: 744914 (The Pile)

Max Activating Token Index: 256

Text #5

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1874986 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9606. Min Act: -0.0000

Data Index: 865116 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1240942 (The Pile)

Max Activating Token Index: 146

Text #8

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1389582 (The Pile)

Max Activating Token Index: 264

Text #9

Max Range: 1.1314. Min Range: -1.1314

Max Act: 1.0054. Min Act: -0.0000

Data Index: 1279512 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9588. Min Act: -0.0000

Data Index: 1177085 (The Pile)

Max Activating Token Index: 56

Text #11

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9412. Min Act: -0.0000

Data Index: 88776 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9313. Min Act: -0.0000

Data Index: 1556053 (The Pile)

Max Activating Token Index: 503

Text #13

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9231. Min Act: -0.0000

Data Index: 66888 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9328. Min Act: -0.0000

Data Index: 154494 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8934. Min Act: -0.0000

Data Index: 898970 (The Pile)

Max Activating Token Index: 518

Text #16

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8917. Min Act: -0.0000

Data Index: 349820 (The Pile)

Max Activating Token Index: 981

Text #17

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9255. Min Act: -0.0000

Data Index: 965876 (The Pile)

Max Activating Token Index: 972

Text #18

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1002556 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1573631 (The Pile)

Max Activating Token Index: 289