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

Dataset: The Pile

Neuron 4094 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: 0.6690. Min Range: -0.6690

Max Act: 0.6396. Min Act: -0.0000

Data Index: 1274240 (The Pile)

Max Activating Token Index: 922

Text #1

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1997612 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.6325. Min Act: -0.0000

Data Index: 756955 (The Pile)

Max Activating Token Index: 730

Text #3

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.6528. Min Act: -0.0000

Data Index: 655346 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.6553. Min Act: -0.0000

Data Index: 958201 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5896. Min Act: -0.0000

Data Index: 462867 (The Pile)

Max Activating Token Index: 621

Text #6

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1900390 (The Pile)

Max Activating Token Index: 892

Text #7

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1843675 (The Pile)

Max Activating Token Index: 562

Text #8

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1428452 (The Pile)

Max Activating Token Index: 183

Text #9

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5901. Min Act: -0.0000

Data Index: 266101 (The Pile)

Max Activating Token Index: 486

Text #10

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5693. Min Act: -0.0000

Data Index: 698639 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5521. Min Act: -0.0000

Data Index: 962875 (The Pile)

Max Activating Token Index: 214

Text #12

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5433. Min Act: -0.0000

Data Index: 106733 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.6034. Min Act: -0.0000

Data Index: 326151 (The Pile)

Max Activating Token Index: 674

Text #14

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1665037 (The Pile)

Max Activating Token Index: 614

Text #15

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1673123 (The Pile)

Max Activating Token Index: 960

Text #16

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1904063 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1175475 (The Pile)

Max Activating Token Index: 585

Text #18

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5704. Min Act: -0.0000

Data Index: 352303 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 0.6690. Min Range: -0.6690

Max Act: 0.5493. Min Act: -0.0000

Data Index: 891527 (The Pile)

Max Activating Token Index: 27