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

Dataset: The Pile

Neuron 2305 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4169. Min Range: -5.4169

Max Act: 5.4169. Min Act: -0.0000

Data Index: 1330627 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 5.4169. Min Range: -5.4169

Max Act: 5.0584. Min Act: -0.0000

Data Index: 870044 (The Pile)

Max Activating Token Index: 119

Text #2

Max Range: 5.4169. Min Range: -5.4169

Max Act: 5.0310. Min Act: -0.0000

Data Index: 425166 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 5.4169. Min Range: -5.4169

Max Act: 5.1753. Min Act: -0.0000

Data Index: 635356 (The Pile)

Max Activating Token Index: 264

Text #4

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.7840. Min Act: -0.0000

Data Index: 765773 (The Pile)

Max Activating Token Index: 358

Text #5

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.9061. Min Act: -0.0000

Data Index: 817132 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 5.4169. Min Range: -5.4169

Max Act: 5.0658. Min Act: -0.0000

Data Index: 672262 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.6497. Min Act: -0.0000

Data Index: 855604 (The Pile)

Max Activating Token Index: 817

Text #8

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.6940. Min Act: -0.0000

Data Index: 1656325 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.6866. Min Act: -0.0000

Data Index: 1138162 (The Pile)

Max Activating Token Index: 592

Text #10

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.5677. Min Act: -0.0000

Data Index: 64858 (The Pile)

Max Activating Token Index: 119

Text #11

Max Range: 5.4169. Min Range: -5.4169

Max Act: 5.0378. Min Act: -0.0000

Data Index: 585131 (The Pile)

Max Activating Token Index: 843

Text #12

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.3703. Min Act: -0.0000

Data Index: 1536564 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.2828. Min Act: -0.0000

Data Index: 1951113 (The Pile)

Max Activating Token Index: 715

Text #14

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.2622. Min Act: -0.0000

Data Index: 1036318 (The Pile)

Max Activating Token Index: 45

Text #15

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.7082. Min Act: -0.0000

Data Index: 1569535 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.2980. Min Act: -0.0000

Data Index: 1114748 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.1376. Min Act: -0.0000

Data Index: 362212 (The Pile)

Max Activating Token Index: 882

Text #18

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.4058. Min Act: -0.0000

Data Index: 1321618 (The Pile)

Max Activating Token Index: 430

Text #19

Max Range: 5.4169. Min Range: -5.4169

Max Act: 4.0281. Min Act: -0.0000

Data Index: 1819834 (The Pile)

Max Activating Token Index: 405