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

Dataset: The Pile

Neuron 4071 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5755. Min Range: -3.5755

Max Act: 3.1495. Min Act: -0.0000

Data Index: 1021245 (The Pile)

Max Activating Token Index: 779

Text #1

Max Range: 3.5755. Min Range: -3.5755

Max Act: 3.5755. Min Act: -0.0000

Data Index: 169487 (The Pile)

Max Activating Token Index: 886

Text #2

Max Range: 3.5755. Min Range: -3.5755

Max Act: 3.1545. Min Act: -0.0000

Data Index: 933463 (The Pile)

Max Activating Token Index: 534

Text #3

Max Range: 3.5755. Min Range: -3.5755

Max Act: 3.1291. Min Act: -0.0000

Data Index: 1320442 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 3.5755. Min Range: -3.5755

Max Act: 3.1337. Min Act: -0.0000

Data Index: 938475 (The Pile)

Max Activating Token Index: 381

Text #5

Max Range: 3.5755. Min Range: -3.5755

Max Act: 3.1204. Min Act: -0.0000

Data Index: 1908804 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 3.5755. Min Range: -3.5755

Max Act: 3.1351. Min Act: -0.0000

Data Index: 593888 (The Pile)

Max Activating Token Index: 363

Text #7

Max Range: 3.5755. Min Range: -3.5755

Max Act: 3.2373. Min Act: -0.0000

Data Index: 990737 (The Pile)

Max Activating Token Index: 338

Text #8

Max Range: 3.5755. Min Range: -3.5755

Max Act: 2.8697. Min Act: -0.0000

Data Index: 440984 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 3.5755. Min Range: -3.5755

Max Act: 2.9936. Min Act: -0.0000

Data Index: 562274 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 3.5755. Min Range: -3.5755

Max Act: 3.1181. Min Act: -0.0000

Data Index: 1915784 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 3.5755. Min Range: -3.5755

Max Act: 2.9118. Min Act: -0.0000

Data Index: 390306 (The Pile)

Max Activating Token Index: 597

Text #12

Max Range: 3.5755. Min Range: -3.5755

Max Act: 3.2043. Min Act: -0.0000

Data Index: 1528643 (The Pile)

Max Activating Token Index: 62

Text #13

Max Range: 3.5755. Min Range: -3.5755

Max Act: 3.2040. Min Act: -0.0000

Data Index: 1897792 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 3.5755. Min Range: -3.5755

Max Act: 2.7181. Min Act: -0.0000

Data Index: 1167019 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 3.5755. Min Range: -3.5755

Max Act: 2.6596. Min Act: -0.0000

Data Index: 230518 (The Pile)

Max Activating Token Index: 103

Text #16

Max Range: 3.5755. Min Range: -3.5755

Max Act: 2.8542. Min Act: -0.0000

Data Index: 1417344 (The Pile)

Max Activating Token Index: 417

Text #17

Max Range: 3.5755. Min Range: -3.5755

Max Act: 3.0971. Min Act: -0.0000

Data Index: 983165 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 3.5755. Min Range: -3.5755

Max Act: 2.5865. Min Act: -0.0000

Data Index: 1123899 (The Pile)

Max Activating Token Index: 115

Text #19

Max Range: 3.5755. Min Range: -3.5755

Max Act: 2.4456. Min Act: -0.0000

Data Index: 474816 (The Pile)

Max Activating Token Index: 420