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

Dataset: The Pile

Neuron 4500 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.1689. Min Act: -0.0000

Data Index: 1354711 (The Pile)

Max Activating Token Index: 806

Text #1

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.2278. Min Act: -0.0000

Data Index: 1263457 (The Pile)

Max Activating Token Index: 588

Text #2

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1560838 (The Pile)

Max Activating Token Index: 378

Text #3

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.0852. Min Act: -0.0000

Data Index: 1733159 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.0156. Min Act: -0.0000

Data Index: 597492 (The Pile)

Max Activating Token Index: 825

Text #5

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1643303 (The Pile)

Max Activating Token Index: 1012

Text #6

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.0441. Min Act: -0.0000

Data Index: 384431 (The Pile)

Max Activating Token Index: 838

Text #7

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.0961. Min Act: -0.0000

Data Index: 193400 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1014246 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1215703 (The Pile)

Max Activating Token Index: 453

Text #10

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1372905 (The Pile)

Max Activating Token Index: 554

Text #11

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1199836 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1468601 (The Pile)

Max Activating Token Index: 773

Text #13

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9842. Min Act: -0.0000

Data Index: 1272662 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1511987 (The Pile)

Max Activating Token Index: 158

Text #15

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9899. Min Act: -0.0000

Data Index: 250514 (The Pile)

Max Activating Token Index: 387

Text #16

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1836332 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9495. Min Act: -0.0000

Data Index: 73156 (The Pile)

Max Activating Token Index: 289

Text #18

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1550101 (The Pile)

Max Activating Token Index: 527

Text #19

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1012594 (The Pile)

Max Activating Token Index: 363