Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5342 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1644. Min Range: -1.1644

Max Act: 1.1644. Min Act: -0.0000

Data Index: 106783 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1490943 (Python Code)

Max Activating Token Index: 824

Text #2

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1072311 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.7808. Min Act: -0.0000

Data Index: 1154895 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.7725. Min Act: -0.0000

Data Index: 1512010 (Python Code)

Max Activating Token Index: 126

Text #5

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.6464. Min Act: -0.0000

Data Index: 281113 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.7510. Min Act: -0.0000

Data Index: 547454 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1396788 (Python Code)

Max Activating Token Index: 1019

Text #8

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.6284. Min Act: -0.0000

Data Index: 501838 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.5938. Min Act: -0.0000

Data Index: 301057 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1411585 (Python Code)

Max Activating Token Index: 255

Text #11

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.6418. Min Act: -0.0000

Data Index: 884552 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1357954 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1089451 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1556891 (Python Code)

Max Activating Token Index: 179

Text #15

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.5580. Min Act: -0.0000

Data Index: 668621 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1180209 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1434721 (Python Code)

Max Activating Token Index: 493

Text #18

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1634952 (Python Code)

Max Activating Token Index: 396

Text #19

Max Range: 1.1644. Min Range: -1.1644

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1519162 (Python Code)

Max Activating Token Index: 272