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

Dataset: The Pile

Neuron 3993 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.4206. Min Act: -0.0000

Data Index: 228353 (The Pile)

Max Activating Token Index: 928

Text #1

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.0624. Min Act: -0.0000

Data Index: 386120 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1071971 (The Pile)

Max Activating Token Index: 957

Text #3

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.9117. Min Act: -0.0000

Data Index: 480969 (The Pile)

Max Activating Token Index: 642

Text #4

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1736395 (The Pile)

Max Activating Token Index: 609

Text #5

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1977946 (The Pile)

Max Activating Token Index: 926

Text #6

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.8962. Min Act: -0.0000

Data Index: 1992584 (The Pile)

Max Activating Token Index: 609

Text #7

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.9060. Min Act: -0.0000

Data Index: 523844 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.9303. Min Act: -0.0000

Data Index: 384827 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.8995. Min Act: -0.0000

Data Index: 244774 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1295587 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.8639. Min Act: -0.0000

Data Index: 671590 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.9863. Min Act: -0.0000

Data Index: 374706 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1370628 (The Pile)

Max Activating Token Index: 595

Text #14

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1514708 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.8385. Min Act: -0.0000

Data Index: 737535 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1731418 (The Pile)

Max Activating Token Index: 200

Text #17

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1701070 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.8365. Min Act: -0.0000

Data Index: 627240 (The Pile)

Max Activating Token Index: 1011

Text #19

Max Range: 1.4206. Min Range: -1.4206

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1335847 (The Pile)

Max Activating Token Index: 991