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

Dataset: The Pile

Neuron 1504 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1849191 (The Pile)

Max Activating Token Index: 446

Text #1

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5535. Min Act: -0.0000

Data Index: 425307 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5075. Min Act: -0.0000

Data Index: 412339 (The Pile)

Max Activating Token Index: 266

Text #3

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5370. Min Act: -0.0000

Data Index: 111918 (The Pile)

Max Activating Token Index: 220

Text #4

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4969. Min Act: -0.0000

Data Index: 594769 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1532359 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4600. Min Act: -0.0000

Data Index: 862642 (The Pile)

Max Activating Token Index: 995

Text #7

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1758221 (The Pile)

Max Activating Token Index: 806

Text #8

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1425524 (The Pile)

Max Activating Token Index: 769

Text #9

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4868. Min Act: -0.0000

Data Index: 360804 (The Pile)

Max Activating Token Index: 164

Text #10

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1248683 (The Pile)

Max Activating Token Index: 964

Text #11

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4822. Min Act: -0.0000

Data Index: 528629 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1418565 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1009857 (The Pile)

Max Activating Token Index: 128

Text #14

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1243053 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4634. Min Act: -0.0000

Data Index: 304802 (The Pile)

Max Activating Token Index: 929

Text #16

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4694. Min Act: -0.0000

Data Index: 625204 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4820. Min Act: -0.0000

Data Index: 599240 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4408. Min Act: -0.0000

Data Index: 206679 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 0.5535. Min Range: -0.5535

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1534258 (The Pile)

Max Activating Token Index: 713