Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5149 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1198990 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.8184. Min Act: -0.0000

Data Index: 432657 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.8606. Min Act: -0.0000

Data Index: 541654 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1091910 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.8697. Min Act: -0.0000

Data Index: 728535 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.8222. Min Act: -0.0000

Data Index: 201347 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1201184 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.8229. Min Act: -0.0000

Data Index: 321691 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.7741. Min Act: -0.0000

Data Index: 629141 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1027616 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.7960. Min Act: -0.0000

Data Index: 356087 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1220931 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.7042. Min Act: -0.0000

Data Index: 62626 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1031812 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.8024. Min Act: -0.0000

Data Index: 306500 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6739. Min Act: -0.0000

Data Index: 971362 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6974. Min Act: -0.0000

Data Index: 434622 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6402. Min Act: -0.0000

Data Index: 953673 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1187561 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6395. Min Act: -0.0000

Data Index: 968515 (C4 (Web Text))

Max Activating Token Index: 116