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

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

Neuron 4892 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: 0.8772. Min Range: -0.8772

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1100849 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.7458. Min Act: -0.0000

Data Index: 448754 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.5695. Min Act: -0.0000

Data Index: 678149 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1089551 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.5284. Min Act: -0.0000

Data Index: 536098 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.4700. Min Act: -0.0000

Data Index: 94415 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.5175. Min Act: -0.0000

Data Index: 732232 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1316105 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.4541. Min Act: -0.0000

Data Index: 726634 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.4486. Min Act: -0.0000

Data Index: 474666 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1127436 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.4399. Min Act: -0.0000

Data Index: 877436 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.4084. Min Act: -0.0000

Data Index: 74174 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.4321. Min Act: -0.0000

Data Index: 653442 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1247685 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.4196. Min Act: -0.0000

Data Index: 662702 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.4288. Min Act: -0.0000

Data Index: 745830 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1346637 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.3872. Min Act: -0.0000

Data Index: 611012 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.8772. Min Range: -0.8772

Max Act: 0.3925. Min Act: -0.0000

Data Index: 485466 (C4 (Web Text))

Max Activating Token Index: 284