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

Dataset: The Pile

Neuron 2587 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: 0.8819. Min Range: -0.8819

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1531982 (The Pile)

Max Activating Token Index: 363

Text #1

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8423. Min Act: -0.0000

Data Index: 200358 (The Pile)

Max Activating Token Index: 802

Text #2

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1312721 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7950. Min Act: -0.0000

Data Index: 1614457 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1191250 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6522. Min Act: -0.0000

Data Index: 25288 (The Pile)

Max Activating Token Index: 632

Text #6

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1467194 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7706. Min Act: -0.0000

Data Index: 1216974 (The Pile)

Max Activating Token Index: 624

Text #8

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6930. Min Act: -0.0000

Data Index: 561476 (The Pile)

Max Activating Token Index: 231

Text #9

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6850. Min Act: -0.0000

Data Index: 424502 (The Pile)

Max Activating Token Index: 524

Text #10

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1165352 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1151130 (The Pile)

Max Activating Token Index: 389

Text #12

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6735. Min Act: -0.0000

Data Index: 588584 (The Pile)

Max Activating Token Index: 778

Text #13

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1198744 (The Pile)

Max Activating Token Index: 876

Text #14

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.5987. Min Act: -0.0000

Data Index: 643888 (The Pile)

Max Activating Token Index: 612

Text #15

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1991741 (The Pile)

Max Activating Token Index: 811

Text #16

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6289. Min Act: -0.0000

Data Index: 609447 (The Pile)

Max Activating Token Index: 817

Text #17

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7082. Min Act: -0.0000

Data Index: 976617 (The Pile)

Max Activating Token Index: 930

Text #18

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1238669 (The Pile)

Max Activating Token Index: 926

Text #19

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6420. Min Act: -0.0000

Data Index: 162093 (The Pile)

Max Activating Token Index: 399