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

Dataset: The Pile

Neuron 1616 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.7613. Min Act: -0.0000

Data Index: 7447 (The Pile)

Max Activating Token Index: 864

Text #1

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1078319 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.7237. Min Act: -0.0000

Data Index: 981743 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1338447 (The Pile)

Max Activating Token Index: 929

Text #4

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6921. Min Act: -0.0000

Data Index: 316080 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1203858 (The Pile)

Max Activating Token Index: 727

Text #6

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6071. Min Act: -0.0000

Data Index: 353008 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6140. Min Act: -0.0000

Data Index: 921099 (The Pile)

Max Activating Token Index: 119

Text #8

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1762580 (The Pile)

Max Activating Token Index: 896

Text #9

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5645. Min Act: -0.0000

Data Index: 25187 (The Pile)

Max Activating Token Index: 933

Text #10

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5808. Min Act: -0.0000

Data Index: 88025 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5937. Min Act: 0.0000

Data Index: 1262161 (The Pile)

Max Activating Token Index: 280

Text #12

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5751. Min Act: -0.0000

Data Index: 244704 (The Pile)

Max Activating Token Index: 274

Text #13

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1414872 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1002320 (The Pile)

Max Activating Token Index: 546

Text #15

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5614. Min Act: 0.0000

Data Index: 508025 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5614. Min Act: -0.0000

Data Index: 533036 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5792. Min Act: -0.0000

Data Index: 896928 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1543072 (The Pile)

Max Activating Token Index: 224

Text #19

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5915. Min Act: -0.0000

Data Index: 375323 (The Pile)

Max Activating Token Index: 298