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

Dataset: The Pile

Neuron 296 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: 7.1881. Min Range: -7.1881

Max Act: 7.1881. Min Act: -0.0000

Data Index: 1775029 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 7.1881. Min Range: -7.1881

Max Act: 6.5083. Min Act: -0.0000

Data Index: 1332199 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 7.1881. Min Range: -7.1881

Max Act: 6.6382. Min Act: -0.0000

Data Index: 934518 (The Pile)

Max Activating Token Index: 18

Text #3

Max Range: 7.1881. Min Range: -7.1881

Max Act: 6.5050. Min Act: -0.0000

Data Index: 1428433 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 7.1881. Min Range: -7.1881

Max Act: 6.1353. Min Act: -0.0000

Data Index: 8973 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 7.1881. Min Range: -7.1881

Max Act: 6.8845. Min Act: -0.0000

Data Index: 586502 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 7.1881. Min Range: -7.1881

Max Act: 6.0592. Min Act: -0.0000

Data Index: 1898331 (The Pile)

Max Activating Token Index: 9

Text #7

Max Range: 7.1881. Min Range: -7.1881

Max Act: 6.1919. Min Act: -0.0000

Data Index: 1133114 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 7.1881. Min Range: -7.1881

Max Act: 5.9800. Min Act: -0.0000

Data Index: 1463116 (The Pile)

Max Activating Token Index: 7

Text #9

Max Range: 7.1881. Min Range: -7.1881

Max Act: 5.8590. Min Act: -0.0000

Data Index: 979439 (The Pile)

Max Activating Token Index: 9

Text #10

Max Range: 7.1881. Min Range: -7.1881

Max Act: 6.0227. Min Act: -0.0000

Data Index: 1359458 (The Pile)

Max Activating Token Index: 9

Text #11

Max Range: 7.1881. Min Range: -7.1881

Max Act: 5.5739. Min Act: -0.0000

Data Index: 200844 (The Pile)

Max Activating Token Index: 998

Text #12

Max Range: 7.1881. Min Range: -7.1881

Max Act: 6.1333. Min Act: -0.0000

Data Index: 1937603 (The Pile)

Max Activating Token Index: 90

Text #13

Max Range: 7.1881. Min Range: -7.1881

Max Act: 5.8890. Min Act: -0.0000

Data Index: 1756523 (The Pile)

Max Activating Token Index: 16

Text #14

Max Range: 7.1881. Min Range: -7.1881

Max Act: 5.4571. Min Act: -0.0000

Data Index: 1872880 (The Pile)

Max Activating Token Index: 11

Text #15

Max Range: 7.1881. Min Range: -7.1881

Max Act: 5.9671. Min Act: -0.0000

Data Index: 272746 (The Pile)

Max Activating Token Index: 11

Text #16

Max Range: 7.1881. Min Range: -7.1881

Max Act: 5.5756. Min Act: -0.0000

Data Index: 664731 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 7.1881. Min Range: -7.1881

Max Act: 5.3060. Min Act: -0.0000

Data Index: 1629133 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 7.1881. Min Range: -7.1881

Max Act: 5.2936. Min Act: -0.0000

Data Index: 1813667 (The Pile)

Max Activating Token Index: 11

Text #19

Max Range: 7.1881. Min Range: -7.1881

Max Act: 5.3932. Min Act: -0.0000

Data Index: 590573 (The Pile)

Max Activating Token Index: 9