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

Dataset: The Pile

Neuron 1886 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: 1.5580. Min Range: -1.5580

Max Act: 1.5580. Min Act: -0.0000

Data Index: 1601045 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.2993. Min Act: -0.0000

Data Index: 1993196 (The Pile)

Max Activating Token Index: 663

Text #2

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.2832. Min Act: -0.0000

Data Index: 1774054 (The Pile)

Max Activating Token Index: 323

Text #3

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.3390. Min Act: -0.0000

Data Index: 604566 (The Pile)

Max Activating Token Index: 431

Text #4

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1080958 (The Pile)

Max Activating Token Index: 407

Text #5

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.3079. Min Act: -0.0000

Data Index: 366817 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1506641 (The Pile)

Max Activating Token Index: 523

Text #7

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.1351. Min Act: -0.0000

Data Index: 220104 (The Pile)

Max Activating Token Index: 843

Text #8

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.3447. Min Act: -0.0000

Data Index: 487614 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.2644. Min Act: -0.0000

Data Index: 1100153 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.2366. Min Act: -0.0000

Data Index: 990474 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.2430. Min Act: -0.0000

Data Index: 77021 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.3086. Min Act: -0.0000

Data Index: 1790992 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.1891. Min Act: -0.0000

Data Index: 349117 (The Pile)

Max Activating Token Index: 345

Text #14

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.2453. Min Act: -0.0000

Data Index: 1897384 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.1447. Min Act: -0.0000

Data Index: 474693 (The Pile)

Max Activating Token Index: 561

Text #16

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.2226. Min Act: -0.0000

Data Index: 500307 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.1617. Min Act: -0.0000

Data Index: 1820386 (The Pile)

Max Activating Token Index: 494

Text #18

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1764600 (The Pile)

Max Activating Token Index: 687

Text #19

Max Range: 1.5580. Min Range: -1.5580

Max Act: 1.1354. Min Act: -0.0000

Data Index: 1124351 (The Pile)

Max Activating Token Index: 466