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

Dataset: The Pile

Neuron 4635 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: 0.7133. Min Range: -0.7133

Max Act: 0.7133. Min Act: -0.0000

Data Index: 656002 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1002612 (The Pile)

Max Activating Token Index: 465

Text #2

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1294667 (The Pile)

Max Activating Token Index: 68

Text #3

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6317. Min Act: -0.0000

Data Index: 779322 (The Pile)

Max Activating Token Index: 260

Text #4

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1349585 (The Pile)

Max Activating Token Index: 302

Text #5

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5797. Min Act: -0.0000

Data Index: 103433 (The Pile)

Max Activating Token Index: 389

Text #6

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1479085 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5645. Min Act: -0.0000

Data Index: 84006 (The Pile)

Max Activating Token Index: 172

Text #8

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5677. Min Act: -0.0000

Data Index: 539710 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5510. Min Act: -0.0000

Data Index: 402138 (The Pile)

Max Activating Token Index: 396

Text #10

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.3642. Min Act: -0.0000

Data Index: 992462 (The Pile)

Max Activating Token Index: 690

Text #11

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1496380 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1714669 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.3922. Min Act: -0.0000

Data Index: 433037 (The Pile)

Max Activating Token Index: 407

Text #14

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5115. Min Act: -0.0000

Data Index: 32676 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1610936 (The Pile)

Max Activating Token Index: 207

Text #16

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1783639 (The Pile)

Max Activating Token Index: 786

Text #17

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1944711 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1404105 (The Pile)

Max Activating Token Index: 320

Text #19

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4731. Min Act: -0.0000

Data Index: 42531 (The Pile)

Max Activating Token Index: 663