Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2248 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.7355. Min Act: -0.0000

Data Index: 1113109 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.4111. Min Act: -0.0000

Data Index: 1384209 (The Pile)

Max Activating Token Index: 94

Text #2

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.6438. Min Act: -0.0000

Data Index: 1861952 (The Pile)

Max Activating Token Index: 840

Text #3

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.3778. Min Act: -0.0000

Data Index: 22139 (The Pile)

Max Activating Token Index: 610

Text #4

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.2042. Min Act: -0.0000

Data Index: 619555 (The Pile)

Max Activating Token Index: 925

Text #5

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.1655. Min Act: -0.0000

Data Index: 1262093 (The Pile)

Max Activating Token Index: 81

Text #6

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.3461. Min Act: -0.0000

Data Index: 1245199 (The Pile)

Max Activating Token Index: 801

Text #7

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.2095. Min Act: -0.0000

Data Index: 1929628 (The Pile)

Max Activating Token Index: 689

Text #8

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.4681. Min Act: -0.0000

Data Index: 181148 (The Pile)

Max Activating Token Index: 816

Text #9

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.5264. Min Act: -0.0000

Data Index: 780420 (The Pile)

Max Activating Token Index: 789

Text #10

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.4468. Min Act: -0.0000

Data Index: 903858 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.1816. Min Act: -0.0000

Data Index: 942512 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.2887. Min Act: -0.0000

Data Index: 327616 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1791507 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.2706. Min Act: -0.0000

Data Index: 1294798 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.1928. Min Act: -0.0000

Data Index: 244017 (The Pile)

Max Activating Token Index: 941

Text #16

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.2275. Min Act: -0.0000

Data Index: 1082490 (The Pile)

Max Activating Token Index: 311

Text #17

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.3832. Min Act: -0.0000

Data Index: 1755141 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.3144. Min Act: -0.0000

Data Index: 367664 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 1.7355. Min Range: -1.7355

Max Act: 1.0546. Min Act: -0.0000

Data Index: 487964 (The Pile)

Max Activating Token Index: 321