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

Dataset: The Pile

Neuron 464 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: 1.7719. Min Range: -1.7719

Max Act: 1.7719. Min Act: 0.0000

Data Index: 485064 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7475. Min Act: -0.0000

Data Index: 1375405 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.6806. Min Act: -0.0000

Data Index: 1826643 (The Pile)

Max Activating Token Index: 802

Text #3

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.5537. Min Act: -0.0000

Data Index: 1877744 (The Pile)

Max Activating Token Index: 850

Text #4

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.4208. Min Act: -0.0000

Data Index: 663510 (The Pile)

Max Activating Token Index: 939

Text #5

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.5805. Min Act: -0.0000

Data Index: 763712 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.5714. Min Act: -0.0000

Data Index: 328933 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.4744. Min Act: -0.0000

Data Index: 1161719 (The Pile)

Max Activating Token Index: 943

Text #8

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.4378. Min Act: -0.0000

Data Index: 366029 (The Pile)

Max Activating Token Index: 900

Text #9

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.4316. Min Act: -0.0000

Data Index: 555152 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.1585. Min Act: -0.0000

Data Index: 641828 (The Pile)

Max Activating Token Index: 564

Text #11

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.3199. Min Act: 0.0001

Data Index: 828315 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.3300. Min Act: -0.0000

Data Index: 412028 (The Pile)

Max Activating Token Index: 756

Text #13

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1765294 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.2857. Min Act: -0.0000

Data Index: 311079 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.3116. Min Act: -0.0000

Data Index: 1819983 (The Pile)

Max Activating Token Index: 49

Text #16

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.2328. Min Act: -0.0000

Data Index: 1641090 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.1779. Min Act: -0.0000

Data Index: 1153861 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.1620. Min Act: -0.0000

Data Index: 446220 (The Pile)

Max Activating Token Index: 278

Text #19

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.0963. Min Act: -0.0000

Data Index: 1338257 (The Pile)

Max Activating Token Index: 411