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

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

Neuron 609 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0822. Min Range: -1.0822

Max Act: 1.0822. Min Act: -0.0001

Data Index: 1202502 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.9868. Min Act: -0.0001

Data Index: 1264310 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 1.0822. Min Range: -1.0822

Max Act: 1.0290. Min Act: -0.0001

Data Index: 850344 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.9705. Min Act: -0.0000

Data Index: 12540 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.9372. Min Act: -0.0001

Data Index: 666971 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.9103. Min Act: -0.0000

Data Index: 1117657 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1029555 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.9117. Min Act: -0.0001

Data Index: 220728 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8985. Min Act: -0.0000

Data Index: 176088 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.9037. Min Act: -0.0001

Data Index: 511663 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8754. Min Act: -0.0000

Data Index: 478006 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8800. Min Act: -0.0001

Data Index: 17307 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8985. Min Act: -0.0001

Data Index: 1109792 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8707. Min Act: -0.0001

Data Index: 378620 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8926. Min Act: -0.0001

Data Index: 317738 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8678. Min Act: -0.0001

Data Index: 977967 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8917. Min Act: -0.0001

Data Index: 794 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1636964 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8908. Min Act: -0.0000

Data Index: 553692 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8570. Min Act: -0.0001

Data Index: 1427922 (Python Code)

Max Activating Token Index: 398