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

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

Neuron 4223 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4880. Min Range: -2.4880

Max Act: 2.3997. Min Act: -0.0000

Data Index: 417376 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 2.4880. Min Range: -2.4880

Max Act: 2.4257. Min Act: -0.0000

Data Index: 192208 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 2.4880. Min Range: -2.4880

Max Act: 2.4781. Min Act: -0.0000

Data Index: 816438 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 2.4880. Min Range: -2.4880

Max Act: 2.4880. Min Act: -0.0000

Data Index: 168370 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 2.4880. Min Range: -2.4880

Max Act: 2.4880. Min Act: -0.0000

Data Index: 185938 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 2.4880. Min Range: -2.4880

Max Act: 2.4477. Min Act: -0.0000

Data Index: 864197 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 2.4880. Min Range: -2.4880

Max Act: 2.2491. Min Act: -0.0000

Data Index: 505940 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 2.4880. Min Range: -2.4880

Max Act: 2.1244. Min Act: -0.0000

Data Index: 44060 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 2.4880. Min Range: -2.4880

Max Act: 2.0051. Min Act: -0.0000

Data Index: 1050608 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 2.4880. Min Range: -2.4880

Max Act: 1.9041. Min Act: -0.0000

Data Index: 88527 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 2.4880. Min Range: -2.4880

Max Act: 1.8753. Min Act: -0.0000

Data Index: 66228 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 2.4880. Min Range: -2.4880

Max Act: 1.7573. Min Act: -0.0000

Data Index: 360369 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 2.4880. Min Range: -2.4880

Max Act: 1.7376. Min Act: -0.0000

Data Index: 371443 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 2.4880. Min Range: -2.4880

Max Act: 1.6214. Min Act: -0.0000

Data Index: 22177 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 2.4880. Min Range: -2.4880

Max Act: 1.5079. Min Act: -0.0000

Data Index: 167630 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 2.4880. Min Range: -2.4880

Max Act: 1.5606. Min Act: -0.0000

Data Index: 1167817 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 2.4880. Min Range: -2.4880

Max Act: 1.4621. Min Act: -0.0000

Data Index: 1296495 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 2.4880. Min Range: -2.4880

Max Act: 1.5529. Min Act: -0.0000

Data Index: 775737 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 2.4880. Min Range: -2.4880

Max Act: 1.4526. Min Act: -0.0000

Data Index: 1221901 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 2.4880. Min Range: -2.4880

Max Act: 1.5703. Min Act: -0.0000

Data Index: 463857 (C4 (Web Text))

Max Activating Token Index: 407