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

Dataset: The Pile

Neuron 4822 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: 0.7334. Min Range: -0.7334

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1995869 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6890. Min Act: -0.0000

Data Index: 997246 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6835. Min Act: -0.0000

Data Index: 528047 (The Pile)

Max Activating Token Index: 156

Text #3

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5706. Min Act: 0.0000

Data Index: 195107 (The Pile)

Max Activating Token Index: 751

Text #4

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6292. Min Act: -0.0000

Data Index: 389939 (The Pile)

Max Activating Token Index: 128

Text #5

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1631734 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6248. Min Act: -0.0000

Data Index: 180211 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.6100. Min Act: 0.0000

Data Index: 1840638 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1206646 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5900. Min Act: -0.0000

Data Index: 164513 (The Pile)

Max Activating Token Index: 913

Text #10

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5960. Min Act: -0.0000

Data Index: 394421 (The Pile)

Max Activating Token Index: 756

Text #11

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5616. Min Act: -0.0000

Data Index: 580268 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5721. Min Act: -0.0000

Data Index: 926382 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5624. Min Act: -0.0000

Data Index: 74207 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5472. Min Act: -0.0000

Data Index: 163492 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5608. Min Act: -0.0000

Data Index: 138648 (The Pile)

Max Activating Token Index: 476

Text #16

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5543. Min Act: 0.0000

Data Index: 381323 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5420. Min Act: -0.0000

Data Index: 690659 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1461325 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 0.7334. Min Range: -0.7334

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1148644 (The Pile)

Max Activating Token Index: 268