Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1917 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.7339. Min Act: -0.0001

Data Index: 226740 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.6412. Min Act: -0.0001

Data Index: 760200 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.6968. Min Act: -0.0001

Data Index: 885330 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.6726. Min Act: -0.0001

Data Index: 159630 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.6772. Min Act: -0.0001

Data Index: 1072941 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.6171. Min Act: -0.0001

Data Index: 564697 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.6124. Min Act: -0.0001

Data Index: 110404 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.6035. Min Act: -0.0001

Data Index: 130611 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.6738. Min Act: -0.0001

Data Index: 485452 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.4837. Min Act: -0.0001

Data Index: 1000175 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.5771. Min Act: -0.0001

Data Index: 1221405 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.5955. Min Act: -0.0001

Data Index: 849059 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.5587. Min Act: -0.0001

Data Index: 661947 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.6110. Min Act: -0.0001

Data Index: 1143161 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.6636. Min Act: -0.0001

Data Index: 303477 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.5532. Min Act: -0.0001

Data Index: 419040 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.6491. Min Act: -0.0001

Data Index: 815763 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.6554. Min Act: -0.0001

Data Index: 1583190 (Python Code)

Max Activating Token Index: 527

Text #18

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.5828. Min Act: -0.0001

Data Index: 1243350 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.7339. Min Range: -0.7339

Max Act: 0.6296. Min Act: -0.0001

Data Index: 275664 (C4 (Web Text))

Max Activating Token Index: 148