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

Dataset: The Pile

Neuron 3421 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1305332 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1641. Min Act: -0.0000

Data Index: 1152809 (The Pile)

Max Activating Token Index: 116

Text #2

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1735507 (The Pile)

Max Activating Token Index: 451

Text #3

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1725. Min Act: -0.0000

Data Index: 193824 (The Pile)

Max Activating Token Index: 485

Text #4

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1892930 (The Pile)

Max Activating Token Index: 923

Text #5

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1533. Min Act: -0.0000

Data Index: 592683 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1474486 (The Pile)

Max Activating Token Index: 901

Text #7

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1607. Min Act: -0.0000

Data Index: 893210 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1521. Min Act: -0.0000

Data Index: 82531 (The Pile)

Max Activating Token Index: 25

Text #9

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1559. Min Act: -0.0000

Data Index: 877163 (The Pile)

Max Activating Token Index: 595

Text #10

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1567. Min Act: -0.0000

Data Index: 645874 (The Pile)

Max Activating Token Index: 771

Text #11

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1369. Min Act: -0.0000

Data Index: 356722 (The Pile)

Max Activating Token Index: 524

Text #12

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1957145 (The Pile)

Max Activating Token Index: 859

Text #13

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1222115 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1535. Min Act: -0.0000

Data Index: 23197 (The Pile)

Max Activating Token Index: 263

Text #15

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1432. Min Act: -0.0000

Data Index: 966886 (The Pile)

Max Activating Token Index: 410

Text #16

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1398254 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1470. Min Act: -0.0000

Data Index: 736526 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1896682 (The Pile)

Max Activating Token Index: 99

Text #19

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1338. Min Act: -0.0000

Data Index: 48960 (The Pile)

Max Activating Token Index: 422