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

Dataset: The Pile

Neuron 3446 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: 0.7510. Min Range: -0.7510

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1071259 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.7510. Min Act: -0.0000

Data Index: 557896 (The Pile)

Max Activating Token Index: 748

Text #2

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1160629 (The Pile)

Max Activating Token Index: 712

Text #3

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1968154 (The Pile)

Max Activating Token Index: 641

Text #4

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1336532 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4327. Min Act: -0.0000

Data Index: 336256 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1711861 (The Pile)

Max Activating Token Index: 586

Text #7

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1072061 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1595678 (The Pile)

Max Activating Token Index: 189

Text #9

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.3742. Min Act: -0.0000

Data Index: 682287 (The Pile)

Max Activating Token Index: 748

Text #10

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4133. Min Act: -0.0000

Data Index: 369530 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4099. Min Act: -0.0000

Data Index: 908565 (The Pile)

Max Activating Token Index: 749

Text #12

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.3705. Min Act: -0.0000

Data Index: 49295 (The Pile)

Max Activating Token Index: 991

Text #13

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.3649. Min Act: -0.0000

Data Index: 527092 (The Pile)

Max Activating Token Index: 427

Text #14

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1664870 (The Pile)

Max Activating Token Index: 883

Text #15

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1508435 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.3558. Min Act: -0.0000

Data Index: 418579 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.3690. Min Act: -0.0000

Data Index: 891185 (The Pile)

Max Activating Token Index: 922

Text #18

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.3436. Min Act: -0.0000

Data Index: 216544 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.3657. Min Act: -0.0000

Data Index: 679101 (The Pile)

Max Activating Token Index: 113