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

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

Neuron 3459 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1029. Min Range: -1.1029

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1119676 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 1.1029. Min Range: -1.1029

Max Act: 1.0436. Min Act: -0.0000

Data Index: 783242 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1047354 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8803. Min Act: -0.0000

Data Index: 1100726 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8862. Min Act: -0.0000

Data Index: 839802 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1614233 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8879. Min Act: -0.0000

Data Index: 306735 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.7612. Min Act: -0.0000

Data Index: 642039 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.7916. Min Act: -0.0000

Data Index: 177748 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.7998. Min Act: -0.0000

Data Index: 651580 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8954. Min Act: -0.0000

Data Index: 159193 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8501. Min Act: -0.0000

Data Index: 1237012 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8288. Min Act: -0.0000

Data Index: 292389 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1619553 (Python Code)

Max Activating Token Index: 725

Text #14

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.7413. Min Act: -0.0000

Data Index: 15409 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.7895. Min Act: -0.0000

Data Index: 729326 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1197443 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.6964. Min Act: -0.0000

Data Index: 663352 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1265728 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 1.1029. Min Range: -1.1029

Max Act: 0.8368. Min Act: -0.0000

Data Index: 907412 (C4 (Web Text))

Max Activating Token Index: 503