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

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

Neuron 1718 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: 1.9637. Min Range: -1.9637

Max Act: 1.9637. Min Act: -0.0000

Data Index: 789010 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.6834. Min Act: -0.0000

Data Index: 532620 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.5794. Min Act: -0.0000

Data Index: 181924 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.7539. Min Act: -0.0000

Data Index: 13690 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.6478. Min Act: -0.0000

Data Index: 647331 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.4926. Min Act: -0.0000

Data Index: 587226 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.5345. Min Act: -0.0000

Data Index: 548548 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.5026. Min Act: -0.0000

Data Index: 1103991 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.4784. Min Act: -0.0000

Data Index: 1075647 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.4657. Min Act: -0.0000

Data Index: 439110 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.4573. Min Act: -0.0000

Data Index: 72554 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.3094. Min Act: -0.0000

Data Index: 499621 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.4465. Min Act: -0.0000

Data Index: 82418 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.4308. Min Act: -0.0000

Data Index: 396886 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.3406. Min Act: -0.0000

Data Index: 778959 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.4135. Min Act: -0.0000

Data Index: 130349 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.3340. Min Act: -0.0000

Data Index: 1196944 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.3708. Min Act: -0.0000

Data Index: 517776 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.2778. Min Act: -0.0000

Data Index: 917861 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 1.9637. Min Range: -1.9637

Max Act: 1.3366. Min Act: -0.0000

Data Index: 1611251 (Python Code)

Max Activating Token Index: 464