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

Dataset: The Pile

Neuron 1161 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: 4.1391. Min Range: -4.1391

Max Act: 4.1391. Min Act: -0.0000

Data Index: 1903332 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 4.1391. Min Range: -4.1391

Max Act: 4.1215. Min Act: -0.0000

Data Index: 1657588 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.9583. Min Act: -0.0000

Data Index: 1822179 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.9219. Min Act: -0.0000

Data Index: 724628 (The Pile)

Max Activating Token Index: 524

Text #4

Max Range: 4.1391. Min Range: -4.1391

Max Act: 4.0274. Min Act: -0.0000

Data Index: 1802068 (The Pile)

Max Activating Token Index: 179

Text #5

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.9758. Min Act: -0.0000

Data Index: 803830 (The Pile)

Max Activating Token Index: 367

Text #6

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.6570. Min Act: -0.0000

Data Index: 1275736 (The Pile)

Max Activating Token Index: 578

Text #7

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.9510. Min Act: -0.0000

Data Index: 50780 (The Pile)

Max Activating Token Index: 179

Text #8

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.9456. Min Act: -0.0000

Data Index: 1751303 (The Pile)

Max Activating Token Index: 54

Text #9

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.6493. Min Act: -0.0000

Data Index: 1339443 (The Pile)

Max Activating Token Index: 973

Text #10

Max Range: 4.1391. Min Range: -4.1391

Max Act: 4.0805. Min Act: -0.0000

Data Index: 905796 (The Pile)

Max Activating Token Index: 48

Text #11

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.8840. Min Act: -0.0000

Data Index: 606074 (The Pile)

Max Activating Token Index: 287

Text #12

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.7008. Min Act: -0.0000

Data Index: 363295 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.7137. Min Act: -0.0000

Data Index: 1946300 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.8694. Min Act: -0.0000

Data Index: 222015 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.6820. Min Act: -0.0000

Data Index: 827463 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.8334. Min Act: -0.0000

Data Index: 422220 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 4.1391. Min Range: -4.1391

Max Act: 4.1366. Min Act: -0.0000

Data Index: 478428 (The Pile)

Max Activating Token Index: 324

Text #18

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.6100. Min Act: -0.0000

Data Index: 1525825 (The Pile)

Max Activating Token Index: 246

Text #19

Max Range: 4.1391. Min Range: -4.1391

Max Act: 3.6113. Min Act: -0.0000

Data Index: 1427628 (The Pile)

Max Activating Token Index: 51