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

Dataset: The Pile

Neuron 2065 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: 1.7158. Min Range: -1.7158

Max Act: 1.7158. Min Act: -0.0000

Data Index: 1151871 (The Pile)

Max Activating Token Index: 536

Text #1

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.7062. Min Act: -0.0000

Data Index: 1837551 (The Pile)

Max Activating Token Index: 214

Text #2

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.6974. Min Act: -0.0000

Data Index: 270151 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.6772. Min Act: -0.0000

Data Index: 382844 (The Pile)

Max Activating Token Index: 489

Text #4

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.5615. Min Act: -0.0000

Data Index: 41134 (The Pile)

Max Activating Token Index: 324

Text #5

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4576. Min Act: -0.0000

Data Index: 986196 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4269. Min Act: -0.0000

Data Index: 122530 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.3949. Min Act: -0.0000

Data Index: 1033860 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4769. Min Act: -0.0000

Data Index: 545985 (The Pile)

Max Activating Token Index: 32

Text #9

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.3649. Min Act: -0.0000

Data Index: 391728 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4412. Min Act: -0.0000

Data Index: 84106 (The Pile)

Max Activating Token Index: 676

Text #11

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4254. Min Act: -0.0000

Data Index: 1031514 (The Pile)

Max Activating Token Index: 298

Text #12

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4096. Min Act: -0.0000

Data Index: 951150 (The Pile)

Max Activating Token Index: 584

Text #13

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.3847. Min Act: -0.0000

Data Index: 1661781 (The Pile)

Max Activating Token Index: 921

Text #14

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1646058 (The Pile)

Max Activating Token Index: 582

Text #15

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.3595. Min Act: -0.0000

Data Index: 593147 (The Pile)

Max Activating Token Index: 667

Text #16

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.3523. Min Act: -0.0000

Data Index: 70577 (The Pile)

Max Activating Token Index: 972

Text #17

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.3474. Min Act: -0.0000

Data Index: 1657082 (The Pile)

Max Activating Token Index: 225

Text #18

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.3321. Min Act: -0.0000

Data Index: 532224 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4030. Min Act: -0.0000

Data Index: 641917 (The Pile)

Max Activating Token Index: 149