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

Dataset: The Pile

Neuron 3538 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8380. Min Range: -5.8380

Max Act: 5.8380. Min Act: -0.0000

Data Index: 886599 (The Pile)

Max Activating Token Index: 645

Text #1

Max Range: 5.8380. Min Range: -5.8380

Max Act: 5.4295. Min Act: -0.0000

Data Index: 1605307 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 5.8380. Min Range: -5.8380

Max Act: 4.3748. Min Act: -0.0000

Data Index: 1428925 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 5.8380. Min Range: -5.8380

Max Act: 4.4982. Min Act: -0.0000

Data Index: 1322226 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 5.8380. Min Range: -5.8380

Max Act: 3.7847. Min Act: -0.0000

Data Index: 1674568 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 5.8380. Min Range: -5.8380

Max Act: 4.3465. Min Act: -0.0000

Data Index: 677509 (The Pile)

Max Activating Token Index: 98

Text #6

Max Range: 5.8380. Min Range: -5.8380

Max Act: 4.1918. Min Act: -0.0000

Data Index: 486637 (The Pile)

Max Activating Token Index: 253

Text #7

Max Range: 5.8380. Min Range: -5.8380

Max Act: 4.2414. Min Act: -0.0000

Data Index: 1457089 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 5.8380. Min Range: -5.8380

Max Act: 4.7284. Min Act: -0.0000

Data Index: 211503 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 5.8380. Min Range: -5.8380

Max Act: 4.0167. Min Act: -0.0000

Data Index: 653692 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 5.8380. Min Range: -5.8380

Max Act: 4.1930. Min Act: -0.0000

Data Index: 708475 (The Pile)

Max Activating Token Index: 503

Text #11

Max Range: 5.8380. Min Range: -5.8380

Max Act: 3.7008. Min Act: -0.0000

Data Index: 1538580 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 5.8380. Min Range: -5.8380

Max Act: 4.7686. Min Act: -0.0000

Data Index: 1627370 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 5.8380. Min Range: -5.8380

Max Act: 4.0940. Min Act: -0.0000

Data Index: 265647 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 5.8380. Min Range: -5.8380

Max Act: 4.5115. Min Act: -0.0000

Data Index: 819772 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 5.8380. Min Range: -5.8380

Max Act: 3.8739. Min Act: -0.0000

Data Index: 1793578 (The Pile)

Max Activating Token Index: 579

Text #16

Max Range: 5.8380. Min Range: -5.8380

Max Act: 4.1774. Min Act: -0.0000

Data Index: 436859 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 5.8380. Min Range: -5.8380

Max Act: 3.5071. Min Act: -0.0000

Data Index: 313267 (The Pile)

Max Activating Token Index: 75

Text #18

Max Range: 5.8380. Min Range: -5.8380

Max Act: 3.5943. Min Act: -0.0000

Data Index: 1851045 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 5.8380. Min Range: -5.8380

Max Act: 3.4158. Min Act: -0.0000

Data Index: 338230 (The Pile)

Max Activating Token Index: 89