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

Dataset: The Pile

Neuron 3207 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: 5.1816. Min Range: -5.1816

Max Act: 5.0016. Min Act: -0.0000

Data Index: 675707 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 5.1816. Min Range: -5.1816

Max Act: 5.1816. Min Act: -0.0000

Data Index: 247611 (The Pile)

Max Activating Token Index: 550

Text #2

Max Range: 5.1816. Min Range: -5.1816

Max Act: 4.9344. Min Act: -0.0000

Data Index: 1516396 (The Pile)

Max Activating Token Index: 560

Text #3

Max Range: 5.1816. Min Range: -5.1816

Max Act: 4.4745. Min Act: -0.0000

Data Index: 565024 (The Pile)

Max Activating Token Index: 681

Text #4

Max Range: 5.1816. Min Range: -5.1816

Max Act: 4.6471. Min Act: -0.0000

Data Index: 1264978 (The Pile)

Max Activating Token Index: 552

Text #5

Max Range: 5.1816. Min Range: -5.1816

Max Act: 4.6127. Min Act: -0.0000

Data Index: 1004649 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 5.1816. Min Range: -5.1816

Max Act: 4.4719. Min Act: -0.0000

Data Index: 1809905 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 5.1816. Min Range: -5.1816

Max Act: 4.2379. Min Act: -0.0000

Data Index: 759045 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 5.1816. Min Range: -5.1816

Max Act: 4.2452. Min Act: -0.0000

Data Index: 1346163 (The Pile)

Max Activating Token Index: 368

Text #9

Max Range: 5.1816. Min Range: -5.1816

Max Act: 4.3966. Min Act: -0.0000

Data Index: 838820 (The Pile)

Max Activating Token Index: 256

Text #10

Max Range: 5.1816. Min Range: -5.1816

Max Act: 3.9642. Min Act: -0.0000

Data Index: 1503531 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 5.1816. Min Range: -5.1816

Max Act: 3.7238. Min Act: -0.0000

Data Index: 1958739 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 5.1816. Min Range: -5.1816

Max Act: 4.0597. Min Act: -0.0000

Data Index: 496932 (The Pile)

Max Activating Token Index: 493

Text #13

Max Range: 5.1816. Min Range: -5.1816

Max Act: 3.5387. Min Act: -0.0000

Data Index: 1473481 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 5.1816. Min Range: -5.1816

Max Act: 3.6456. Min Act: -0.0000

Data Index: 1171974 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 5.1816. Min Range: -5.1816

Max Act: 3.7386. Min Act: -0.0000

Data Index: 701824 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 5.1816. Min Range: -5.1816

Max Act: 3.5019. Min Act: -0.0000

Data Index: 1524838 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 5.1816. Min Range: -5.1816

Max Act: 3.5541. Min Act: -0.0000

Data Index: 897094 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 5.1816. Min Range: -5.1816

Max Act: 3.4074. Min Act: -0.0000

Data Index: 904425 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 5.1816. Min Range: -5.1816

Max Act: 3.4034. Min Act: -0.0000

Data Index: 1188616 (The Pile)

Max Activating Token Index: 537