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

Dataset: The Pile

Neuron 1428 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: 0.7251. Min Range: -0.7251

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1904898 (The Pile)

Max Activating Token Index: 1007

Text #1

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1597617 (The Pile)

Max Activating Token Index: 753

Text #2

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1756351 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5435. Min Act: -0.0000

Data Index: 439904 (The Pile)

Max Activating Token Index: 562

Text #4

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1120862 (The Pile)

Max Activating Token Index: 944

Text #5

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5396. Min Act: -0.0000

Data Index: 992303 (The Pile)

Max Activating Token Index: 211

Text #6

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1695772 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1568813 (The Pile)

Max Activating Token Index: 91

Text #8

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4905. Min Act: -0.0000

Data Index: 821457 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1829515 (The Pile)

Max Activating Token Index: 376

Text #10

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5179. Min Act: -0.0000

Data Index: 12064 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4783. Min Act: -0.0000

Data Index: 1700069 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1290610 (The Pile)

Max Activating Token Index: 960

Text #13

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4254. Min Act: -0.0000

Data Index: 721488 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1661205 (The Pile)

Max Activating Token Index: 699

Text #15

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1189166 (The Pile)

Max Activating Token Index: 544

Text #16

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4355. Min Act: -0.0000

Data Index: 263884 (The Pile)

Max Activating Token Index: 232

Text #17

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4664. Min Act: -0.0000

Data Index: 566799 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1718277 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4395. Min Act: -0.0000

Data Index: 452993 (The Pile)

Max Activating Token Index: 394