Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2702 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.1252. Min Range: -5.1252

Max Act: 5.1252. Min Act: -0.0000

Data Index: 1249302 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.7591. Min Act: -0.0000

Data Index: 458872 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.7048. Min Act: -0.0000

Data Index: 609364 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.5796. Min Act: -0.0000

Data Index: 1087591 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.5757. Min Act: -0.0000

Data Index: 1273747 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.5644. Min Act: -0.0000

Data Index: 1286797 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.6354. Min Act: -0.0000

Data Index: 793447 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.4628. Min Act: -0.0000

Data Index: 664004 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.6336. Min Act: -0.0000

Data Index: 58383 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.4358. Min Act: -0.0000

Data Index: 669806 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.3468. Min Act: -0.0000

Data Index: 302986 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.3685. Min Act: -0.0000

Data Index: 783583 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.3456. Min Act: -0.0000

Data Index: 512026 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.4901. Min Act: -0.0000

Data Index: 1122270 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.0877. Min Act: -0.0000

Data Index: 586568 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.0919. Min Act: -0.0000

Data Index: 1182000 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.2282. Min Act: -0.0000

Data Index: 607947 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.3609. Min Act: -0.0000

Data Index: 653934 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 5.1252. Min Range: -5.1252

Max Act: 4.3391. Min Act: -0.0000

Data Index: 188759 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 5.1252. Min Range: -5.1252

Max Act: 3.9863. Min Act: -0.0000

Data Index: 235894 (C4 (Web Text))

Max Activating Token Index: 34