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

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

Neuron 3347 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: 1.3521. Min Range: -1.3521

Max Act: 1.3521. Min Act: -0.0000

Data Index: 1220975 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.2636. Min Act: -0.0001

Data Index: 782128 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1759. Min Act: -0.0000

Data Index: 488368 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1972. Min Act: -0.0000

Data Index: 229038 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1910. Min Act: -0.0001

Data Index: 289184 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1672. Min Act: -0.0001

Data Index: 607261 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1817. Min Act: -0.0000

Data Index: 1144528 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1668. Min Act: -0.0000

Data Index: 1079444 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0253. Min Act: -0.0001

Data Index: 873939 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1037. Min Act: -0.0001

Data Index: 1189699 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0553. Min Act: -0.0001

Data Index: 518988 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0653. Min Act: -0.0000

Data Index: 498596 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0291. Min Act: -0.0001

Data Index: 168355 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1173. Min Act: -0.0001

Data Index: 413947 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0696. Min Act: -0.0000

Data Index: 1204395 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.8894. Min Act: -0.0001

Data Index: 790872 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9723. Min Act: -0.0001

Data Index: 954818 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9702. Min Act: -0.0001

Data Index: 1280730 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1202440 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1014806 (C4 (Web Text))

Max Activating Token Index: 403