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

Dataset: The Pile

Neuron 4506 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: 0.7588. Min Range: -0.7588

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1785367 (The Pile)

Max Activating Token Index: 346

Text #1

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.6033. Min Act: -0.0000

Data Index: 891090 (The Pile)

Max Activating Token Index: 613

Text #2

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.6354. Min Act: -0.0000

Data Index: 926458 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5886. Min Act: -0.0000

Data Index: 232020 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1070652 (The Pile)

Max Activating Token Index: 544

Text #5

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5816. Min Act: -0.0000

Data Index: 333032 (The Pile)

Max Activating Token Index: 454

Text #6

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1161806 (The Pile)

Max Activating Token Index: 872

Text #7

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5469. Min Act: -0.0000

Data Index: 483108 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5577. Min Act: -0.0000

Data Index: 23258 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1362486 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5890. Min Act: -0.0000

Data Index: 133587 (The Pile)

Max Activating Token Index: 320

Text #11

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1950120 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.6200. Min Act: -0.0000

Data Index: 349957 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5623. Min Act: -0.0001

Data Index: 742225 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5276. Min Act: -0.0000

Data Index: 47436 (The Pile)

Max Activating Token Index: 365

Text #15

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5917. Min Act: -0.0000

Data Index: 90100 (The Pile)

Max Activating Token Index: 475

Text #16

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1273717 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5188. Min Act: -0.0001

Data Index: 801543 (The Pile)

Max Activating Token Index: 459

Text #18

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1015345 (The Pile)

Max Activating Token Index: 636

Text #19

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4337. Min Act: -0.0000

Data Index: 911190 (The Pile)

Max Activating Token Index: 972