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

Dataset: The Pile

Neuron 2493 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5363. Min Act: -0.0000

Data Index: 1910813 (The Pile)

Max Activating Token Index: 315

Text #1

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5531. Min Act: -0.0000

Data Index: 1965517 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1769515 (The Pile)

Max Activating Token Index: 987

Text #3

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5019. Min Act: -0.0000

Data Index: 890106 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5112. Min Act: -0.0000

Data Index: 898179 (The Pile)

Max Activating Token Index: 295

Text #5

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5061. Min Act: -0.0000

Data Index: 737592 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1165227 (The Pile)

Max Activating Token Index: 653

Text #7

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1181782 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4701. Min Act: -0.0000

Data Index: 757937 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1336081 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1983434 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4236. Min Act: -0.0000

Data Index: 700472 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1539602 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4625. Min Act: -0.0000

Data Index: 100422 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4312. Min Act: -0.0000

Data Index: 72263 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4290. Min Act: -0.0000

Data Index: 326545 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1798486 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4062. Min Act: -0.0000

Data Index: 386695 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4165. Min Act: -0.0000

Data Index: 941165 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4232. Min Act: -0.0000

Data Index: 45991 (The Pile)

Max Activating Token Index: 178