Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3988 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.6629. Min Range: -3.6629

Max Act: 3.6629. Min Act: -0.0000

Data Index: 182984 (The Pile)

Max Activating Token Index: 393

Text #1

Max Range: 3.6629. Min Range: -3.6629

Max Act: 3.5317. Min Act: -0.0000

Data Index: 1906890 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 3.6629. Min Range: -3.6629

Max Act: 3.0469. Min Act: -0.0000

Data Index: 1585455 (The Pile)

Max Activating Token Index: 364

Text #3

Max Range: 3.6629. Min Range: -3.6629

Max Act: 3.0692. Min Act: -0.0000

Data Index: 969657 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.8657. Min Act: -0.0000

Data Index: 465691 (The Pile)

Max Activating Token Index: 930

Text #5

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.6586. Min Act: -0.0000

Data Index: 1292300 (The Pile)

Max Activating Token Index: 256

Text #6

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.6436. Min Act: -0.0000

Data Index: 1017569 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.6089. Min Act: -0.0000

Data Index: 1277340 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.7012. Min Act: -0.0000

Data Index: 964217 (The Pile)

Max Activating Token Index: 231

Text #9

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.4481. Min Act: -0.0000

Data Index: 376940 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.0241. Min Act: -0.0000

Data Index: 1036544 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.1419. Min Act: -0.0000

Data Index: 532688 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.2469. Min Act: -0.0000

Data Index: 923547 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.0291. Min Act: -0.0000

Data Index: 186916 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.5636. Min Act: -0.0000

Data Index: 16873 (The Pile)

Max Activating Token Index: 395

Text #15

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.0822. Min Act: -0.0000

Data Index: 131708 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.3927. Min Act: -0.0000

Data Index: 574227 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.0648. Min Act: -0.0000

Data Index: 1897489 (The Pile)

Max Activating Token Index: 23

Text #18

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.2545. Min Act: -0.0000

Data Index: 1261897 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.1079. Min Act: -0.0000

Data Index: 1317716 (The Pile)

Max Activating Token Index: 978