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

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

Neuron 2928 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.9785. Min Act: -0.0000

Data Index: 921051 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.9847. Min Act: -0.0000

Data Index: 145965 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8938. Min Act: -0.0000

Data Index: 700456 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8128. Min Act: -0.0000

Data Index: 51112 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.9075. Min Act: -0.0000

Data Index: 108000 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1335576 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8535. Min Act: -0.0000

Data Index: 666370 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1053048 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8695. Min Act: -0.0000

Data Index: 838273 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1315399 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8505. Min Act: -0.0000

Data Index: 1137828 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7780. Min Act: -0.0000

Data Index: 567963 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8239. Min Act: -0.0000

Data Index: 769195 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1097786 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8144. Min Act: -0.0000

Data Index: 678810 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7469. Min Act: -0.0000

Data Index: 81626 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7771. Min Act: -0.0000

Data Index: 25343 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7686. Min Act: -0.0000

Data Index: 23136 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1311058 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7391. Min Act: -0.0000

Data Index: 715432 (C4 (Web Text))

Max Activating Token Index: 464