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

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

Neuron 910 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0037. Min Range: -1.0037

Max Act: 1.0037. Min Act: -0.0001

Data Index: 441944 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.8806. Min Act: -0.0001

Data Index: 903705 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.9929. Min Act: -0.0001

Data Index: 749397 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.9386. Min Act: -0.0001

Data Index: 1546990 (Python Code)

Max Activating Token Index: 411

Text #4

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.8248. Min Act: -0.0001

Data Index: 430979 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.9055. Min Act: -0.0001

Data Index: 831500 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.8790. Min Act: -0.0001

Data Index: 80274 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.9373. Min Act: -0.0001

Data Index: 923571 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.7893. Min Act: -0.0001

Data Index: 483115 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.8834. Min Act: -0.0001

Data Index: 307782 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.9004. Min Act: -0.0001

Data Index: 310923 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.9311. Min Act: -0.0001

Data Index: 897582 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.9749. Min Act: -0.0001

Data Index: 1391364 (Python Code)

Max Activating Token Index: 864

Text #13

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.7696. Min Act: -0.0001

Data Index: 716887 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.9149. Min Act: -0.0001

Data Index: 681928 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.7962. Min Act: -0.0001

Data Index: 112046 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.7564. Min Act: -0.0001

Data Index: 904019 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.8987. Min Act: -0.0001

Data Index: 1953 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.7804. Min Act: -0.0001

Data Index: 1149399 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 1.0037. Min Range: -1.0037

Max Act: 0.7542. Min Act: -0.0001

Data Index: 740729 (C4 (Web Text))

Max Activating Token Index: 771