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

Dataset: The Pile

Neuron 3299 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: 0.4831. Min Range: -0.4831

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1047432 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.4434. Min Act: -0.0000

Data Index: 75063 (The Pile)

Max Activating Token Index: 670

Text #2

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3795. Min Act: -0.0000

Data Index: 223810 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1674558 (The Pile)

Max Activating Token Index: 267

Text #4

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.4158. Min Act: -0.0000

Data Index: 434311 (The Pile)

Max Activating Token Index: 17

Text #5

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.4106. Min Act: -0.0000

Data Index: 307819 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3349. Min Act: -0.0000

Data Index: 600460 (The Pile)

Max Activating Token Index: 533

Text #7

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3995. Min Act: -0.0000

Data Index: 1136191 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1184809 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.4122. Min Act: -0.0000

Data Index: 727538 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.4045. Min Act: -0.0000

Data Index: 607250 (The Pile)

Max Activating Token Index: 393

Text #11

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3852. Min Act: -0.0000

Data Index: 604128 (The Pile)

Max Activating Token Index: 571

Text #12

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3986. Min Act: -0.0000

Data Index: 318372 (The Pile)

Max Activating Token Index: 501

Text #13

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1076011 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3704. Min Act: -0.0000

Data Index: 390029 (The Pile)

Max Activating Token Index: 25

Text #15

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3912. Min Act: -0.0000

Data Index: 738088 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1919605 (The Pile)

Max Activating Token Index: 103

Text #17

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3773. Min Act: -0.0000

Data Index: 743988 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1016288 (The Pile)

Max Activating Token Index: 282

Text #19

Max Range: 0.4831. Min Range: -0.4831

Max Act: 0.3835. Min Act: -0.0000

Data Index: 843635 (The Pile)

Max Activating Token Index: 67