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

Dataset: The Pile

Neuron 2549 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: 0.7473. Min Range: -0.7473

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1446230 (The Pile)

Max Activating Token Index: 670

Text #1

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6075. Min Act: -0.0000

Data Index: 703384 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1609323 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1266930 (The Pile)

Max Activating Token Index: 546

Text #4

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5467. Min Act: -0.0000

Data Index: 192603 (The Pile)

Max Activating Token Index: 357

Text #5

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1510543 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1671212 (The Pile)

Max Activating Token Index: 455

Text #7

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1123883 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1039919 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4797. Min Act: -0.0000

Data Index: 499568 (The Pile)

Max Activating Token Index: 550

Text #10

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1201327 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4903. Min Act: -0.0000

Data Index: 329714 (The Pile)

Max Activating Token Index: 814

Text #12

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1158736 (The Pile)

Max Activating Token Index: 896

Text #13

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1947080 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1799505 (The Pile)

Max Activating Token Index: 791

Text #15

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4338. Min Act: -0.0000

Data Index: 553079 (The Pile)

Max Activating Token Index: 710

Text #16

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4539. Min Act: -0.0000

Data Index: 694884 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4691. Min Act: -0.0000

Data Index: 965887 (The Pile)

Max Activating Token Index: 509

Text #18

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4311. Min Act: -0.0000

Data Index: 193511 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1852920 (The Pile)

Max Activating Token Index: 198