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

Dataset: The Pile

Neuron 4107 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: 3.4452. Min Range: -3.4452

Max Act: 3.3749. Min Act: -0.0000

Data Index: 1636409 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.3246. Min Act: -0.0000

Data Index: 191526 (The Pile)

Max Activating Token Index: 649

Text #2

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.3246. Min Act: -0.0000

Data Index: 1020066 (The Pile)

Max Activating Token Index: 753

Text #3

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.4318. Min Act: -0.0000

Data Index: 1343471 (The Pile)

Max Activating Token Index: 886

Text #4

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.2497. Min Act: -0.0000

Data Index: 854062 (The Pile)

Max Activating Token Index: 7

Text #5

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.3829. Min Act: -0.0000

Data Index: 387359 (The Pile)

Max Activating Token Index: 961

Text #6

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.0387. Min Act: -0.0000

Data Index: 1383797 (The Pile)

Max Activating Token Index: 691

Text #7

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.3468. Min Act: -0.0000

Data Index: 1017074 (The Pile)

Max Activating Token Index: 7

Text #8

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.3081. Min Act: -0.0000

Data Index: 476865 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.9747. Min Act: -0.0000

Data Index: 948062 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.8038. Min Act: -0.0000

Data Index: 1202579 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.4132. Min Act: -0.0000

Data Index: 220179 (The Pile)

Max Activating Token Index: 188

Text #12

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.2190. Min Act: -0.0000

Data Index: 994793 (The Pile)

Max Activating Token Index: 434

Text #13

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.3472. Min Act: -0.0000

Data Index: 1519132 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.9033. Min Act: -0.0000

Data Index: 1868235 (The Pile)

Max Activating Token Index: 955

Text #15

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.4452. Min Act: -0.0000

Data Index: 1326607 (The Pile)

Max Activating Token Index: 899

Text #16

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.2733. Min Act: -0.0000

Data Index: 322575 (The Pile)

Max Activating Token Index: 230

Text #17

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.1368. Min Act: -0.0000

Data Index: 1994713 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.2782. Min Act: -0.0000

Data Index: 1492188 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.9422. Min Act: -0.0000

Data Index: 1217551 (The Pile)

Max Activating Token Index: 18