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

Dataset: The Pile

Neuron 3452 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.7537. Min Act: -0.0000

Data Index: 433217 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1768236 (The Pile)

Max Activating Token Index: 953

Text #2

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.6929. Min Act: -0.0000

Data Index: 435880 (The Pile)

Max Activating Token Index: 549

Text #3

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.6427. Min Act: -0.0000

Data Index: 670829 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1229165 (The Pile)

Max Activating Token Index: 738

Text #5

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1680743 (The Pile)

Max Activating Token Index: 963

Text #6

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.6086. Min Act: -0.0000

Data Index: 467346 (The Pile)

Max Activating Token Index: 614

Text #7

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5193. Min Act: -0.0000

Data Index: 698061 (The Pile)

Max Activating Token Index: 922

Text #8

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.6226. Min Act: -0.0000

Data Index: 781141 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1469365 (The Pile)

Max Activating Token Index: 218

Text #10

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1794418 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5710. Min Act: -0.0000

Data Index: 68651 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.4773. Min Act: -0.0000

Data Index: 493314 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5210. Min Act: -0.0000

Data Index: 681945 (The Pile)

Max Activating Token Index: 174

Text #14

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.6067. Min Act: -0.0000

Data Index: 856769 (The Pile)

Max Activating Token Index: 585

Text #15

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5254. Min Act: -0.0000

Data Index: 430636 (The Pile)

Max Activating Token Index: 396

Text #16

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1062119 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5387. Min Act: -0.0000

Data Index: 581223 (The Pile)

Max Activating Token Index: 826

Text #18

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1904979 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 0.7537. Min Range: -0.7537

Max Act: 0.4879. Min Act: -0.0000

Data Index: 775010 (The Pile)

Max Activating Token Index: 849