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

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

Neuron 326 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.3879. Min Act: -0.0001

Data Index: 1572747 (Python Code)

Max Activating Token Index: 673

Text #1

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.2559. Min Act: -0.0000

Data Index: 1263721 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.2023. Min Act: -0.0000

Data Index: 529030 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.2353. Min Act: -0.0000

Data Index: 1507297 (Python Code)

Max Activating Token Index: 69

Text #4

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.2087. Min Act: -0.0000

Data Index: 847417 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.1635. Min Act: -0.0000

Data Index: 690400 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.1953. Min Act: -0.0001

Data Index: 1216284 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.2281. Min Act: -0.0000

Data Index: 334722 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.0931. Min Act: -0.0000

Data Index: 671896 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.1569. Min Act: -0.0000

Data Index: 320848 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.0901. Min Act: -0.0000

Data Index: 381076 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.1594. Min Act: -0.0000

Data Index: 1451886 (Python Code)

Max Activating Token Index: 847

Text #12

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.1515. Min Act: -0.0000

Data Index: 527825 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1536222 (Python Code)

Max Activating Token Index: 265

Text #14

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.1141. Min Act: -0.0000

Data Index: 725731 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.0677. Min Act: -0.0000

Data Index: 700350 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.0982. Min Act: -0.0000

Data Index: 479715 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.0977. Min Act: -0.0000

Data Index: 625551 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.0518. Min Act: -0.0000

Data Index: 1479387 (Python Code)

Max Activating Token Index: 995

Text #19

Max Range: 1.3879. Min Range: -1.3879

Max Act: 1.0791. Min Act: -0.0001

Data Index: 1622798 (Python Code)

Max Activating Token Index: 825