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

Dataset: The Pile

Neuron 2363 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6197. Min Range: -3.6197

Max Act: 3.6197. Min Act: -0.0000

Data Index: 833948 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 3.6197. Min Range: -3.6197

Max Act: 3.2481. Min Act: -0.0000

Data Index: 1053921 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 3.6197. Min Range: -3.6197

Max Act: 3.3742. Min Act: -0.0000

Data Index: 986871 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 3.6197. Min Range: -3.6197

Max Act: 3.3636. Min Act: -0.0000

Data Index: 1890797 (The Pile)

Max Activating Token Index: 224

Text #4

Max Range: 3.6197. Min Range: -3.6197

Max Act: 3.1958. Min Act: -0.0000

Data Index: 1451594 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 3.6197. Min Range: -3.6197

Max Act: 3.0186. Min Act: -0.0000

Data Index: 508656 (The Pile)

Max Activating Token Index: 762

Text #6

Max Range: 3.6197. Min Range: -3.6197

Max Act: 3.1770. Min Act: -0.0000

Data Index: 1172777 (The Pile)

Max Activating Token Index: 376

Text #7

Max Range: 3.6197. Min Range: -3.6197

Max Act: 3.0051. Min Act: -0.0000

Data Index: 1506343 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 3.6197. Min Range: -3.6197

Max Act: 2.9857. Min Act: -0.0000

Data Index: 622989 (The Pile)

Max Activating Token Index: 99

Text #9

Max Range: 3.6197. Min Range: -3.6197

Max Act: 2.9880. Min Act: -0.0000

Data Index: 1557487 (The Pile)

Max Activating Token Index: 563

Text #10

Max Range: 3.6197. Min Range: -3.6197

Max Act: 3.1465. Min Act: -0.0000

Data Index: 723916 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 3.6197. Min Range: -3.6197

Max Act: 2.8712. Min Act: -0.0000

Data Index: 38847 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 3.6197. Min Range: -3.6197

Max Act: 2.8627. Min Act: -0.0000

Data Index: 1686620 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 3.6197. Min Range: -3.6197

Max Act: 3.1131. Min Act: -0.0000

Data Index: 740914 (The Pile)

Max Activating Token Index: 741

Text #14

Max Range: 3.6197. Min Range: -3.6197

Max Act: 2.6640. Min Act: -0.0000

Data Index: 980458 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 3.6197. Min Range: -3.6197

Max Act: 2.7640. Min Act: -0.0000

Data Index: 1998114 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 3.6197. Min Range: -3.6197

Max Act: 2.6224. Min Act: -0.0000

Data Index: 1590583 (The Pile)

Max Activating Token Index: 6

Text #17

Max Range: 3.6197. Min Range: -3.6197

Max Act: 2.6224. Min Act: -0.0000

Data Index: 1684873 (The Pile)

Max Activating Token Index: 6

Text #18

Max Range: 3.6197. Min Range: -3.6197

Max Act: 2.7406. Min Act: -0.0000

Data Index: 1431246 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 3.6197. Min Range: -3.6197

Max Act: 2.3801. Min Act: -0.0000

Data Index: 931314 (The Pile)

Max Activating Token Index: 572