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

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

Neuron 637 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.2518. Min Act: -0.0000

Data Index: 991428 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.8824. Min Act: -0.0001

Data Index: 1009432 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.8085. Min Act: -0.0000

Data Index: 657648 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.8305. Min Act: -0.0000

Data Index: 722130 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.8517. Min Act: -0.0000

Data Index: 299314 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.7957. Min Act: -0.0000

Data Index: 130923 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.8123. Min Act: -0.0001

Data Index: 42425 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.7931. Min Act: -0.0000

Data Index: 289290 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.7546. Min Act: -0.0000

Data Index: 528373 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.7724. Min Act: -0.0001

Data Index: 1278168 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.8035. Min Act: -0.0000

Data Index: 476114 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.7581. Min Act: -0.0000

Data Index: 582263 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.7328. Min Act: -0.0001

Data Index: 1062943 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.7648. Min Act: -0.0001

Data Index: 566188 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.7343. Min Act: -0.0000

Data Index: 610655 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.7513. Min Act: -0.0000

Data Index: 839076 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1192209 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.6992. Min Act: -0.0001

Data Index: 272379 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.7021. Min Act: -0.0000

Data Index: 239694 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 1.2518. Min Range: -1.2518

Max Act: 0.6635. Min Act: -0.0000

Data Index: 208024 (C4 (Web Text))

Max Activating Token Index: 613