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

Dataset: The Pile

Neuron 3730 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: 0.1930. Min Range: -0.1930

Max Act: 0.1930. Min Act: -0.0000

Data Index: 628309 (The Pile)

Max Activating Token Index: 759

Text #1

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1009903 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1579. Min Act: -0.0000

Data Index: 1021714 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1070308 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1548. Min Act: -0.0000

Data Index: 1337437 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1631. Min Act: -0.0000

Data Index: 1373482 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1301207 (The Pile)

Max Activating Token Index: 72

Text #7

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1486424 (The Pile)

Max Activating Token Index: 817

Text #8

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1459. Min Act: -0.0000

Data Index: 487475 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1505. Min Act: -0.0000

Data Index: 290095 (The Pile)

Max Activating Token Index: 650

Text #10

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1088679 (The Pile)

Max Activating Token Index: 836

Text #11

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1714. Min Act: -0.0000

Data Index: 883578 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1753222 (The Pile)

Max Activating Token Index: 777

Text #13

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1382. Min Act: -0.0000

Data Index: 638712 (The Pile)

Max Activating Token Index: 901

Text #14

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1312. Min Act: -0.0000

Data Index: 98106 (The Pile)

Max Activating Token Index: 984

Text #15

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1364. Min Act: -0.0000

Data Index: 553285 (The Pile)

Max Activating Token Index: 330

Text #16

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1311. Min Act: -0.0000

Data Index: 551658 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1227. Min Act: -0.0000

Data Index: 674014 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1428410 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1091121 (The Pile)

Max Activating Token Index: 145