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

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

Neuron 2648 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.4426. Min Act: -0.0000

Data Index: 136930 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.5542. Min Act: -0.0001

Data Index: 626524 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.8692. Min Act: -0.0001

Data Index: 1106633 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.8607. Min Act: -0.0001

Data Index: 640663 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.7163. Min Act: -0.0000

Data Index: 545655 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.9783. Min Act: -0.0001

Data Index: 203689 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.7799. Min Act: -0.0001

Data Index: 1282500 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.4200. Min Act: -0.0001

Data Index: 25552 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.6647. Min Act: -0.0001

Data Index: 896876 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.6416. Min Act: -0.0000

Data Index: 704137 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.5701. Min Act: -0.0000

Data Index: 1254243 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.5713. Min Act: -0.0000

Data Index: 968946 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.5658. Min Act: -0.0001

Data Index: 211482 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.5481. Min Act: -0.0000

Data Index: 370350 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.5408. Min Act: -0.0000

Data Index: 121012 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.5219. Min Act: -0.0000

Data Index: 156943 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.4984. Min Act: -0.0001

Data Index: 143731 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.6201. Min Act: -0.0001

Data Index: 305957 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.3413. Min Act: -0.0001

Data Index: 826462 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 3.5542. Min Range: -3.5542

Max Act: 2.4549. Min Act: -0.0000

Data Index: 204441 (C4 (Web Text))

Max Activating Token Index: 43