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

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

Neuron 4750 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4887. Min Act: -0.0000

Data Index: 356639 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.1798. Min Act: -0.0000

Data Index: 1308486 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.8948. Min Act: -0.0000

Data Index: 260863 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.5954. Min Act: -0.0000

Data Index: 423885 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.8549. Min Act: -0.0000

Data Index: 310179 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.7141. Min Act: -0.0000

Data Index: 1187246 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.5664. Min Act: -0.0000

Data Index: 628169 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.7836. Min Act: -0.0000

Data Index: 1016485 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.7885. Min Act: -0.0000

Data Index: 268629 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.6006. Min Act: -0.0000

Data Index: 776267 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.7420. Min Act: -0.0000

Data Index: 273145 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.5980. Min Act: -0.0000

Data Index: 648481 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.4659. Min Act: -0.0000

Data Index: 1257070 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.7205. Min Act: -0.0000

Data Index: 147965 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.5858. Min Act: -0.0000

Data Index: 618166 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.5612. Min Act: -0.0000

Data Index: 177628 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.6932. Min Act: -0.0000

Data Index: 712448 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.4810. Min Act: -0.0000

Data Index: 34480 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.4761. Min Act: -0.0000

Data Index: 1297759 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 3.4887. Min Range: -3.4887

Max Act: 2.5897. Min Act: -0.0000

Data Index: 661386 (C4 (Web Text))

Max Activating Token Index: 504