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

Dataset: The Pile

Neuron 2738 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: 0.4008. Min Range: -0.4008

Max Act: 0.4008. Min Act: -0.0000

Data Index: 636403 (The Pile)

Max Activating Token Index: 615

Text #1

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1340740 (The Pile)

Max Activating Token Index: 601

Text #2

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3638. Min Act: -0.0000

Data Index: 432993 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1507867 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3800. Min Act: -0.0000

Data Index: 35142 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3914. Min Act: -0.0000

Data Index: 491041 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3694. Min Act: -0.0000

Data Index: 200684 (The Pile)

Max Activating Token Index: 298

Text #7

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3794. Min Act: -0.0000

Data Index: 949416 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3190. Min Act: -0.0000

Data Index: 816722 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1997675 (The Pile)

Max Activating Token Index: 892

Text #10

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3370. Min Act: -0.0000

Data Index: 138852 (The Pile)

Max Activating Token Index: 477

Text #11

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3473. Min Act: -0.0000

Data Index: 824304 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1345650 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3213. Min Act: -0.0000

Data Index: 430657 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1663500 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3223. Min Act: -0.0000

Data Index: 466597 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1861149 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1681315 (The Pile)

Max Activating Token Index: 552

Text #18

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3395. Min Act: -0.0000

Data Index: 717461 (The Pile)

Max Activating Token Index: 475

Text #19

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3158. Min Act: -0.0000

Data Index: 966985 (The Pile)

Max Activating Token Index: 253