Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 563 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1083898 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.6189. Min Act: -0.0000

Data Index: 620744 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.6334. Min Act: -0.0000

Data Index: 661172 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.6237. Min Act: -0.0000

Data Index: 602306 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5822. Min Act: -0.0000

Data Index: 728321 (The Pile)

Max Activating Token Index: 245

Text #5

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5799. Min Act: -0.0000

Data Index: 594934 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5699. Min Act: -0.0000

Data Index: 919040 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1954561 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4633. Min Act: -0.0000

Data Index: 896688 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1720103 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1508017 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1182840 (The Pile)

Max Activating Token Index: 52

Text #12

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1285428 (The Pile)

Max Activating Token Index: 611

Text #13

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1609751 (The Pile)

Max Activating Token Index: 956

Text #14

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1976404 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1432824 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4505. Min Act: -0.0000

Data Index: 806146 (The Pile)

Max Activating Token Index: 457

Text #17

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5118. Min Act: -0.0000

Data Index: 93535 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1132806 (The Pile)

Max Activating Token Index: 446

Text #19

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4812. Min Act: -0.0000

Data Index: 97408 (The Pile)

Max Activating Token Index: 56