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

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

Neuron 4066 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0710. Min Range: -1.0710

Max Act: 1.0710. Min Act: -0.0000

Data Index: 520442 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 1.0710. Min Range: -1.0710

Max Act: 1.0154. Min Act: -0.0000

Data Index: 182728 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9925. Min Act: -0.0000

Data Index: 1234457 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9869. Min Act: -0.0000

Data Index: 4246 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8799. Min Act: -0.0000

Data Index: 643053 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9116. Min Act: -0.0000

Data Index: 207903 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8616. Min Act: -0.0000

Data Index: 235533 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8444. Min Act: -0.0000

Data Index: 303010 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7857. Min Act: -0.0000

Data Index: 872391 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7773. Min Act: -0.0000

Data Index: 773499 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1149234 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8117. Min Act: -0.0000

Data Index: 508791 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1029952 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1114778 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7908. Min Act: -0.0000

Data Index: 148620 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8416. Min Act: -0.0000

Data Index: 279706 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1255957 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1078738 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8037. Min Act: -0.0000

Data Index: 707100 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7517. Min Act: -0.0000

Data Index: 280657 (C4 (Web Text))

Max Activating Token Index: 375