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

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

Neuron 3386 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: 1.8967. Min Range: -1.8967

Max Act: 1.8966. Min Act: -0.0000

Data Index: 1123338 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.8946. Min Act: -0.0000

Data Index: 778057 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.8967. Min Act: -0.0000

Data Index: 47258 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.7922. Min Act: -0.0000

Data Index: 1189477 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.7463. Min Act: -0.0000

Data Index: 68493 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.7611. Min Act: -0.0000

Data Index: 673396 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.7435. Min Act: -0.0000

Data Index: 845848 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.6627. Min Act: -0.0000

Data Index: 1042947 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.6928. Min Act: -0.0000

Data Index: 238503 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.6721. Min Act: -0.0000

Data Index: 1170755 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.6750. Min Act: -0.0000

Data Index: 328700 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.6527. Min Act: -0.0000

Data Index: 146305 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.6309. Min Act: -0.0000

Data Index: 281934 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.5839. Min Act: -0.0000

Data Index: 824332 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.6037. Min Act: -0.0000

Data Index: 106625 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.6115. Min Act: -0.0000

Data Index: 712576 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.4647. Min Act: -0.0000

Data Index: 101818 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.6486. Min Act: -0.0000

Data Index: 1129716 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.6000. Min Act: -0.0000

Data Index: 966587 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.5721. Min Act: -0.0000

Data Index: 1109973 (C4 (Web Text))

Max Activating Token Index: 94