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

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

Neuron 3422 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: 0.0939. Min Range: -0.0939

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1283268 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0939. Min Act: -0.0000

Data Index: 218606 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0750. Min Act: -0.0000

Data Index: 752533 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0880. Min Act: -0.0000

Data Index: 592368 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0753. Min Act: -0.0000

Data Index: 1570496 (Python Code)

Max Activating Token Index: 820

Text #5

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1223872 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0732. Min Act: -0.0000

Data Index: 1444081 (Python Code)

Max Activating Token Index: 922

Text #7

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0776. Min Act: -0.0000

Data Index: 164353 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1338245 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0767. Min Act: -0.0000

Data Index: 1369568 (Python Code)

Max Activating Token Index: 989

Text #10

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0765. Min Act: -0.0000

Data Index: 963390 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1644681 (Python Code)

Max Activating Token Index: 700

Text #12

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0703. Min Act: -0.0001

Data Index: 1451478 (Python Code)

Max Activating Token Index: 505

Text #13

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0808. Min Act: -0.0000

Data Index: 426538 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1059241 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1651257 (Python Code)

Max Activating Token Index: 928

Text #16

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1385086 (Python Code)

Max Activating Token Index: 596

Text #17

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0758. Min Act: -0.0000

Data Index: 657921 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0693. Min Act: -0.0000

Data Index: 525211 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0725. Min Act: -0.0000

Data Index: 447662 (C4 (Web Text))

Max Activating Token Index: 977