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

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

Neuron 600 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0545. Min Range: -3.0545

Max Act: 3.0545. Min Act: -0.0000

Data Index: 834259 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 3.0545. Min Range: -3.0545

Max Act: 3.0050. Min Act: -0.0000

Data Index: 707306 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.5155. Min Act: -0.0000

Data Index: 5179 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.9565. Min Act: -0.0000

Data Index: 341144 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.5725. Min Act: -0.0001

Data Index: 548764 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.3111. Min Act: -0.0000

Data Index: 491484 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.2727. Min Act: -0.0001

Data Index: 754282 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.1194. Min Act: -0.0000

Data Index: 1063706 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.3092. Min Act: -0.0000

Data Index: 1099707 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.4073. Min Act: -0.0000

Data Index: 1143806 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.0491. Min Act: -0.0000

Data Index: 649670 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.2566. Min Act: -0.0000

Data Index: 159623 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.0961. Min Act: -0.0000

Data Index: 108138 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.0865. Min Act: -0.0000

Data Index: 1280853 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 3.0545. Min Range: -3.0545

Max Act: 1.9767. Min Act: -0.0000

Data Index: 1350571 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.0306. Min Act: -0.0000

Data Index: 749385 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 3.0545. Min Range: -3.0545

Max Act: 1.9335. Min Act: -0.0000

Data Index: 1090805 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 3.0545. Min Range: -3.0545

Max Act: 2.1446. Min Act: -0.0000

Data Index: 86482 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 3.0545. Min Range: -3.0545

Max Act: 1.9986. Min Act: -0.0000

Data Index: 1039644 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 3.0545. Min Range: -3.0545

Max Act: 1.8995. Min Act: -0.0000

Data Index: 1170814 (C4 (Web Text))

Max Activating Token Index: 582