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

Dataset: The Pile

Neuron 3707 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: 0.7072. Min Range: -0.7072

Max Act: 0.7072. Min Act: -0.0000

Data Index: 151548 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5866. Min Act: -0.0000

Data Index: 786471 (The Pile)

Max Activating Token Index: 591

Text #2

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5239. Min Act: -0.0000

Data Index: 991334 (The Pile)

Max Activating Token Index: 307

Text #3

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1646532 (The Pile)

Max Activating Token Index: 938

Text #4

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4120. Min Act: -0.0000

Data Index: 714740 (The Pile)

Max Activating Token Index: 737

Text #5

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4762. Min Act: -0.0000

Data Index: 473821 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.3765. Min Act: -0.0000

Data Index: 280850 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1822179 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1102996 (The Pile)

Max Activating Token Index: 716

Text #9

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4042. Min Act: -0.0000

Data Index: 468093 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1295863 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.3745. Min Act: -0.0000

Data Index: 902726 (The Pile)

Max Activating Token Index: 1008

Text #12

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.3984. Min Act: -0.0000

Data Index: 1017986 (The Pile)

Max Activating Token Index: 615

Text #13

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1593740 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1868646 (The Pile)

Max Activating Token Index: 699

Text #15

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1418379 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1603971 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1924159 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.3648. Min Act: -0.0000

Data Index: 319530 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1814275 (The Pile)

Max Activating Token Index: 501