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

Dataset: The Pile

Neuron 2386 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: 1.1955. Min Range: -1.1955

Max Act: 1.1955. Min Act: -0.0000

Data Index: 190535 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8780. Min Act: -0.0000

Data Index: 409037 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1425946 (The Pile)

Max Activating Token Index: 598

Text #3

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9544. Min Act: -0.0000

Data Index: 134240 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8678. Min Act: -0.0000

Data Index: 285958 (The Pile)

Max Activating Token Index: 294

Text #5

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8735. Min Act: -0.0000

Data Index: 370296 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8439. Min Act: -0.0000

Data Index: 21924 (The Pile)

Max Activating Token Index: 931

Text #7

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9161. Min Act: -0.0000

Data Index: 829487 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8918. Min Act: -0.0000

Data Index: 1617634 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8433. Min Act: -0.0000

Data Index: 357350 (The Pile)

Max Activating Token Index: 625

Text #10

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1916560 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8968. Min Act: -0.0000

Data Index: 1787668 (The Pile)

Max Activating Token Index: 874

Text #12

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1343206 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8422. Min Act: -0.0000

Data Index: 435752 (The Pile)

Max Activating Token Index: 42

Text #14

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8053. Min Act: -0.0000

Data Index: 601967 (The Pile)

Max Activating Token Index: 733

Text #15

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.7292. Min Act: -0.0000

Data Index: 773381 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8009. Min Act: -0.0000

Data Index: 946331 (The Pile)

Max Activating Token Index: 760

Text #17

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8447. Min Act: -0.0000

Data Index: 286438 (The Pile)

Max Activating Token Index: 322

Text #18

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1023188 (The Pile)

Max Activating Token Index: 49

Text #19

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1442580 (The Pile)

Max Activating Token Index: 486