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

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

Neuron 4198 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1079635 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5856. Min Act: -0.0000

Data Index: 60757 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5630. Min Act: -0.0000

Data Index: 59130 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5472. Min Act: -0.0000

Data Index: 698574 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5297. Min Act: -0.0000

Data Index: 848012 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1414589 (Python Code)

Max Activating Token Index: 799

Text #6

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5171. Min Act: -0.0000

Data Index: 357914 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5012. Min Act: -0.0000

Data Index: 655300 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1419299 (Python Code)

Max Activating Token Index: 263

Text #9

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4814. Min Act: -0.0000

Data Index: 309068 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.5077. Min Act: -0.0000

Data Index: 621072 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4752. Min Act: -0.0000

Data Index: 401748 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1137542 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4559. Min Act: -0.0000

Data Index: 311814 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4388. Min Act: -0.0000

Data Index: 80148 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4385. Min Act: -0.0000

Data Index: 57757 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4477. Min Act: -0.0000

Data Index: 82944 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1283879 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1063962 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.6605. Min Range: -0.6605

Max Act: 0.4337. Min Act: -0.0000

Data Index: 727152 (C4 (Web Text))

Max Activating Token Index: 821