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

Dataset: The Pile

Neuron 2512 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1432062 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.7429. Min Act: -0.0000

Data Index: 678539 (The Pile)

Max Activating Token Index: 94

Text #2

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6937. Min Act: -0.0000

Data Index: 99975 (The Pile)

Max Activating Token Index: 225

Text #3

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6996. Min Act: 0.0000

Data Index: 1952920 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6837. Min Act: -0.0000

Data Index: 902983 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1494975 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.5645. Min Act: -0.0000

Data Index: 645184 (The Pile)

Max Activating Token Index: 346

Text #7

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1125627 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.5625. Min Act: -0.0000

Data Index: 327215 (The Pile)

Max Activating Token Index: 1018

Text #9

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.5528. Min Act: -0.0000

Data Index: 173699 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.5278. Min Act: -0.0000

Data Index: 968749 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.5320. Min Act: 0.0000

Data Index: 457818 (The Pile)

Max Activating Token Index: 575

Text #12

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1813244 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1657152 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.5191. Min Act: 0.0000

Data Index: 1132735 (The Pile)

Max Activating Token Index: 697

Text #15

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.5129. Min Act: -0.0000

Data Index: 727644 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.4997. Min Act: -0.0000

Data Index: 288349 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.5652. Min Act: -0.0000

Data Index: 524381 (The Pile)

Max Activating Token Index: 739

Text #18

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.5652. Min Act: -0.0000

Data Index: 172139 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 0.7519. Min Range: -0.7519

Max Act: 0.4938. Min Act: 0.0000

Data Index: 321607 (The Pile)

Max Activating Token Index: 193