Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3855 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.4889. Min Act: -0.0000

Data Index: 466670 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1594752 (The Pile)

Max Activating Token Index: 758

Text #2

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1959196 (The Pile)

Max Activating Token Index: 511

Text #3

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1696927 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1290341 (The Pile)

Max Activating Token Index: 882

Text #5

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1989595 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3388. Min Act: -0.0000

Data Index: 920814 (The Pile)

Max Activating Token Index: 947

Text #7

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2998. Min Act: -0.0000

Data Index: 279113 (The Pile)

Max Activating Token Index: 766

Text #8

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1555023 (The Pile)

Max Activating Token Index: 167

Text #9

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1802585 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3409. Min Act: -0.0000

Data Index: 290 (The Pile)

Max Activating Token Index: 837

Text #11

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1146443 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1849058 (The Pile)

Max Activating Token Index: 602

Text #13

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3546. Min Act: -0.0000

Data Index: 622541 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3010. Min Act: -0.0000

Data Index: 250031 (The Pile)

Max Activating Token Index: 21

Text #15

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1880567 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3052. Min Act: -0.0000

Data Index: 613291 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1468395 (The Pile)

Max Activating Token Index: 98

Text #18

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1039334 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 0.4889. Min Range: -0.4889

Max Act: 0.3219. Min Act: -0.0000

Data Index: 974504 (The Pile)

Max Activating Token Index: 371