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

Dataset: The Pile

Neuron 3203 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: 1.4084. Min Range: -1.4084

Max Act: 1.4084. Min Act: -0.0000

Data Index: 1448015 (The Pile)

Max Activating Token Index: 144

Text #1

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.3216. Min Act: -0.0000

Data Index: 469796 (The Pile)

Max Activating Token Index: 800

Text #2

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.3268. Min Act: -0.0000

Data Index: 122181 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.2578. Min Act: -0.0000

Data Index: 136387 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.3342. Min Act: -0.0000

Data Index: 1798569 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.2470. Min Act: -0.0000

Data Index: 668611 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.2535. Min Act: -0.0000

Data Index: 40598 (The Pile)

Max Activating Token Index: 65

Text #7

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.1720. Min Act: -0.0000

Data Index: 1551928 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1640162 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.0776. Min Act: -0.0000

Data Index: 615403 (The Pile)

Max Activating Token Index: 94

Text #10

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.0771. Min Act: -0.0000

Data Index: 1514200 (The Pile)

Max Activating Token Index: 843

Text #11

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.1249. Min Act: -0.0000

Data Index: 131247 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.1876. Min Act: -0.0000

Data Index: 1897720 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.0590. Min Act: -0.0000

Data Index: 1516579 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.0949. Min Act: -0.0000

Data Index: 202134 (The Pile)

Max Activating Token Index: 806

Text #15

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.0981. Min Act: -0.0000

Data Index: 575690 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.1739. Min Act: -0.0000

Data Index: 1522949 (The Pile)

Max Activating Token Index: 964

Text #17

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.0318. Min Act: -0.0000

Data Index: 261421 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.1606. Min Act: -0.0000

Data Index: 365139 (The Pile)

Max Activating Token Index: 796

Text #19

Max Range: 1.4084. Min Range: -1.4084

Max Act: 1.0834. Min Act: -0.0000

Data Index: 61372 (The Pile)

Max Activating Token Index: 417