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

Dataset: The Pile

Neuron 2646 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: 0.5565. Min Range: -0.5565

Max Act: 0.5565. Min Act: -0.0000

Data Index: 356260 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4414. Min Act: -0.0000

Data Index: 578789 (The Pile)

Max Activating Token Index: 243

Text #2

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1690766 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4402. Min Act: -0.0000

Data Index: 890867 (The Pile)

Max Activating Token Index: 46

Text #4

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1105661 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1903894 (The Pile)

Max Activating Token Index: 222

Text #6

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1298937 (The Pile)

Max Activating Token Index: 85

Text #7

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1948286 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3847. Min Act: -0.0000

Data Index: 592270 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4078. Min Act: -0.0000

Data Index: 131666 (The Pile)

Max Activating Token Index: 609

Text #10

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1688999 (The Pile)

Max Activating Token Index: 408

Text #11

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1908769 (The Pile)

Max Activating Token Index: 284

Text #12

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3810. Min Act: -0.0000

Data Index: 75394 (The Pile)

Max Activating Token Index: 949

Text #13

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3997. Min Act: -0.0000

Data Index: 622569 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3836. Min Act: -0.0000

Data Index: 533560 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1231562 (The Pile)

Max Activating Token Index: 634

Text #16

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1219149 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3555. Min Act: -0.0000

Data Index: 861228 (The Pile)

Max Activating Token Index: 812

Text #18

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3907. Min Act: -0.0000

Data Index: 1937343 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 0.5565. Min Range: -0.5565

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1484642 (The Pile)

Max Activating Token Index: 641