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

Dataset: The Pile

Neuron 1848 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.3067. Min Range: -3.3067

Max Act: 3.3067. Min Act: -0.0000

Data Index: 1444937 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 3.3067. Min Range: -3.3067

Max Act: 3.1472. Min Act: -0.0000

Data Index: 1429626 (The Pile)

Max Activating Token Index: 618

Text #2

Max Range: 3.3067. Min Range: -3.3067

Max Act: 3.0831. Min Act: -0.0000

Data Index: 1034828 (The Pile)

Max Activating Token Index: 523

Text #3

Max Range: 3.3067. Min Range: -3.3067

Max Act: 3.2578. Min Act: -0.0000

Data Index: 1546940 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 3.3067. Min Range: -3.3067

Max Act: 3.1381. Min Act: -0.0000

Data Index: 1183570 (The Pile)

Max Activating Token Index: 517

Text #5

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.9771. Min Act: -0.0000

Data Index: 839340 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.7181. Min Act: -0.0000

Data Index: 1023444 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.7043. Min Act: -0.0000

Data Index: 1226543 (The Pile)

Max Activating Token Index: 363

Text #8

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.8276. Min Act: -0.0000

Data Index: 1965449 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.6784. Min Act: -0.0000

Data Index: 1674515 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.6375. Min Act: -0.0000

Data Index: 1107731 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 3.3067. Min Range: -3.3067

Max Act: 3.0514. Min Act: -0.0000

Data Index: 469981 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.7216. Min Act: -0.0000

Data Index: 488821 (The Pile)

Max Activating Token Index: 565

Text #13

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.5932. Min Act: -0.0000

Data Index: 768479 (The Pile)

Max Activating Token Index: 401

Text #14

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.8527. Min Act: -0.0000

Data Index: 16212 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.8313. Min Act: -0.0000

Data Index: 953874 (The Pile)

Max Activating Token Index: 719

Text #16

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.6732. Min Act: -0.0000

Data Index: 515569 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.6831. Min Act: -0.0000

Data Index: 694946 (The Pile)

Max Activating Token Index: 275

Text #18

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.5694. Min Act: -0.0000

Data Index: 1615657 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 3.3067. Min Range: -3.3067

Max Act: 2.5359. Min Act: -0.0000

Data Index: 529905 (The Pile)

Max Activating Token Index: 885