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

Dataset: The Pile

Neuron 1687 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: 1.0898. Min Range: -1.0898

Max Act: 1.0898. Min Act: -0.0001

Data Index: 241066 (The Pile)

Max Activating Token Index: 491

Text #1

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1374405 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8920. Min Act: -0.0000

Data Index: 586498 (The Pile)

Max Activating Token Index: 281

Text #3

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1548150 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1365885 (The Pile)

Max Activating Token Index: 145

Text #5

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8784. Min Act: -0.0000

Data Index: 902601 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1401411 (The Pile)

Max Activating Token Index: 566

Text #7

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8933. Min Act: -0.0000

Data Index: 965668 (The Pile)

Max Activating Token Index: 435

Text #8

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1776311 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1440343 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.9234. Min Act: -0.0000

Data Index: 766446 (The Pile)

Max Activating Token Index: 620

Text #11

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8580. Min Act: -0.0000

Data Index: 101987 (The Pile)

Max Activating Token Index: 297

Text #12

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1762510 (The Pile)

Max Activating Token Index: 835

Text #13

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8796. Min Act: -0.0000

Data Index: 1868530 (The Pile)

Max Activating Token Index: 564

Text #14

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8536. Min Act: -0.0000

Data Index: 219946 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1259051 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8730. Min Act: -0.0000

Data Index: 631744 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8778. Min Act: -0.0000

Data Index: 695273 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8691. Min Act: -0.0000

Data Index: 955641 (The Pile)

Max Activating Token Index: 708

Text #19

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8923. Min Act: -0.0001

Data Index: 1831939 (The Pile)

Max Activating Token Index: 796