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

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

Neuron 1990 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: 1.1478. Min Range: -1.1478

Max Act: 1.1478. Min Act: -0.0000

Data Index: 152281 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 1.1478. Min Range: -1.1478

Max Act: 1.1426. Min Act: -0.0000

Data Index: 1244824 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 1.1478. Min Range: -1.1478

Max Act: 1.0480. Min Act: -0.0000

Data Index: 490343 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 1.1478. Min Range: -1.1478

Max Act: 1.0620. Min Act: -0.0000

Data Index: 764515 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 1.1478. Min Range: -1.1478

Max Act: 1.0160. Min Act: -0.0000

Data Index: 1174957 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 1.1478. Min Range: -1.1478

Max Act: 1.0132. Min Act: -0.0000

Data Index: 326840 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 1.1478. Min Range: -1.1478

Max Act: 1.0032. Min Act: -0.0000

Data Index: 343941 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 1.1478. Min Range: -1.1478

Max Act: 1.0334. Min Act: -0.0000

Data Index: 138500 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 1.1478. Min Range: -1.1478

Max Act: 1.0259. Min Act: -0.0000

Data Index: 1221082 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 1.1478. Min Range: -1.1478

Max Act: 1.0793. Min Act: -0.0000

Data Index: 443926 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 1.1478. Min Range: -1.1478

Max Act: 1.0384. Min Act: -0.0000

Data Index: 957783 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.9676. Min Act: -0.0000

Data Index: 447042 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.9656. Min Act: -0.0000

Data Index: 789628 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.9831. Min Act: -0.0000

Data Index: 704380 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.9752. Min Act: -0.0000

Data Index: 364837 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.9807. Min Act: -0.0000

Data Index: 225352 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 1.1478. Min Range: -1.1478

Max Act: 1.0298. Min Act: -0.0000

Data Index: 826233 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.9486. Min Act: -0.0000

Data Index: 276432 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.8920. Min Act: -0.0000

Data Index: 248645 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.8916. Min Act: -0.0000

Data Index: 188064 (C4 (Web Text))

Max Activating Token Index: 21