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

Dataset: The Pile

Neuron 2908 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: 0.9504. Min Range: -0.9504

Max Act: 0.9312. Min Act: -0.0000

Data Index: 826932 (The Pile)

Max Activating Token Index: 296

Text #1

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1525103 (The Pile)

Max Activating Token Index: 527

Text #2

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1665015 (The Pile)

Max Activating Token Index: 595

Text #3

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.9504. Min Act: -0.0000

Data Index: 1152045 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1391765 (The Pile)

Max Activating Token Index: 488

Text #5

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.8484. Min Act: -0.0000

Data Index: 623842 (The Pile)

Max Activating Token Index: 851

Text #6

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1389997 (The Pile)

Max Activating Token Index: 725

Text #7

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7167. Min Act: -0.0000

Data Index: 624262 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1633244 (The Pile)

Max Activating Token Index: 588

Text #9

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1841198 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6681. Min Act: -0.0000

Data Index: 835763 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6173. Min Act: -0.0000

Data Index: 921166 (The Pile)

Max Activating Token Index: 563

Text #12

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1321122 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6484. Min Act: -0.0000

Data Index: 898509 (The Pile)

Max Activating Token Index: 143

Text #14

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1819520 (The Pile)

Max Activating Token Index: 938

Text #15

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6351. Min Act: -0.0000

Data Index: 1792259 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.4824. Min Act: -0.0000

Data Index: 438880 (The Pile)

Max Activating Token Index: 888

Text #17

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1491393 (The Pile)

Max Activating Token Index: 658

Text #18

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.4515. Min Act: -0.0000

Data Index: 389173 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1610966 (The Pile)

Max Activating Token Index: 503