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

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

Neuron 2363 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.6091. Min Act: -0.0000

Data Index: 362590 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.6328. Min Act: -0.0000

Data Index: 80581 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5894. Min Act: -0.0000

Data Index: 757361 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5673. Min Act: -0.0000

Data Index: 831107 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5192. Min Act: -0.0000

Data Index: 373756 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.5331. Min Act: -0.0000

Data Index: 995674 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4963. Min Act: -0.0000

Data Index: 640436 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4766. Min Act: -0.0000

Data Index: 197752 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4853. Min Act: -0.0000

Data Index: 954602 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4772. Min Act: -0.0000

Data Index: 560414 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4616. Min Act: -0.0000

Data Index: 925415 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4712. Min Act: -0.0000

Data Index: 297152 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1322835 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4786. Min Act: -0.0000

Data Index: 100771 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4758. Min Act: -0.0000

Data Index: 435404 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4743. Min Act: -0.0000

Data Index: 836316 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4723. Min Act: -0.0000

Data Index: 198565 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4425. Min Act: -0.0000

Data Index: 986799 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4518. Min Act: -0.0000

Data Index: 772839 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.6328. Min Range: -0.6328

Max Act: 0.4360. Min Act: -0.0000

Data Index: 571859 (C4 (Web Text))

Max Activating Token Index: 728