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

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

Neuron 4623 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1451. Min Range: -1.1451

Max Act: 1.1074. Min Act: -0.0000

Data Index: 40447 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.1451. Min Range: -1.1451

Max Act: 1.1451. Min Act: -0.0000

Data Index: 714607 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.9797. Min Act: 0.0000

Data Index: 1183773 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8827. Min Act: -0.0000

Data Index: 679864 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8709. Min Act: -0.0000

Data Index: 867471 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8462. Min Act: -0.0000

Data Index: 763755 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1281710 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1318038 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.8669. Min Act: -0.0000

Data Index: 275495 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7993. Min Act: -0.0000

Data Index: 207702 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7029. Min Act: -0.0000

Data Index: 835229 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7636. Min Act: -0.0000

Data Index: 237331 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7412. Min Act: -0.0000

Data Index: 430873 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7331. Min Act: -0.0000

Data Index: 731274 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7234. Min Act: -0.0000

Data Index: 676405 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1027738 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7108. Min Act: -0.0000

Data Index: 76861 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1294442 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.7030. Min Act: -0.0000

Data Index: 424703 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 1.1451. Min Range: -1.1451

Max Act: 0.6998. Min Act: -0.0000

Data Index: 366664 (C4 (Web Text))

Max Activating Token Index: 701