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

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

Neuron 3529 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0812. Min Range: -2.0812

Max Act: 2.0141. Min Act: -0.0000

Data Index: 720070 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 2.0812. Min Range: -2.0812

Max Act: 2.0747. Min Act: -0.0000

Data Index: 230623 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.9016. Min Act: -0.0000

Data Index: 592131 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 2.0812. Min Range: -2.0812

Max Act: 2.0812. Min Act: -0.0000

Data Index: 50676 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.9758. Min Act: -0.0000

Data Index: 690336 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.8361. Min Act: -0.0000

Data Index: 1163257 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.8448. Min Act: -0.0000

Data Index: 1012331 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 2.0812. Min Range: -2.0812

Max Act: 2.0308. Min Act: -0.0000

Data Index: 860704 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.8038. Min Act: -0.0000

Data Index: 1118802 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.7689. Min Act: -0.0000

Data Index: 1452751 (Python Code)

Max Activating Token Index: 329

Text #10

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.8585. Min Act: -0.0000

Data Index: 1010910 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.8570. Min Act: -0.0000

Data Index: 835966 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.6312. Min Act: -0.0000

Data Index: 228892 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.7279. Min Act: -0.0000

Data Index: 1299853 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.9359. Min Act: -0.0000

Data Index: 1060928 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.7140. Min Act: -0.0000

Data Index: 842305 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.7153. Min Act: -0.0000

Data Index: 723637 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.7007. Min Act: -0.0000

Data Index: 1340712 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.6978. Min Act: -0.0000

Data Index: 855178 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 2.0812. Min Range: -2.0812

Max Act: 1.7829. Min Act: -0.0000

Data Index: 474380 (C4 (Web Text))

Max Activating Token Index: 592