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

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

Neuron 4697 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: 2.9617. Min Range: -2.9617

Max Act: 2.9373. Min Act: -0.0000

Data Index: 558361 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.9617. Min Act: -0.0000

Data Index: 867690 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.8703. Min Act: -0.0000

Data Index: 1078762 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.7754. Min Act: -0.0000

Data Index: 336912 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.6052. Min Act: -0.0000

Data Index: 993147 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.5564. Min Act: -0.0000

Data Index: 699351 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.3982. Min Act: -0.0000

Data Index: 636267 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.3577. Min Act: -0.0000

Data Index: 959191 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.3753. Min Act: -0.0000

Data Index: 1293844 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.5093. Min Act: -0.0000

Data Index: 733469 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.4936. Min Act: -0.0000

Data Index: 1317931 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.3922. Min Act: -0.0000

Data Index: 296796 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.5905. Min Act: -0.0000

Data Index: 1029609 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.6036. Min Act: -0.0000

Data Index: 720464 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.5870. Min Act: -0.0000

Data Index: 898750 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.2905. Min Act: -0.0000

Data Index: 1246688 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.2943. Min Act: -0.0000

Data Index: 933371 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.4945. Min Act: -0.0000

Data Index: 1310143 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.4994. Min Act: -0.0000

Data Index: 1321182 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 2.9617. Min Range: -2.9617

Max Act: 2.3553. Min Act: -0.0000

Data Index: 544303 (C4 (Web Text))

Max Activating Token Index: 62