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

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

Neuron 4441 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: 0.8948. Min Range: -0.8948

Max Act: 0.8948. Min Act: -0.0000

Data Index: 1219 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6782. Min Act: -0.0000

Data Index: 6810 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1035225 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6877. Min Act: -0.0000

Data Index: 736236 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6348. Min Act: -0.0000

Data Index: 28013 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6536. Min Act: -0.0000

Data Index: 408199 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6929. Min Act: -0.0000

Data Index: 78397 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6820. Min Act: -0.0000

Data Index: 735855 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6723. Min Act: -0.0000

Data Index: 145930 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1305958 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1244108 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6115. Min Act: -0.0000

Data Index: 971008 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1605360 (Python Code)

Max Activating Token Index: 520

Text #13

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6486. Min Act: -0.0000

Data Index: 618673 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1436528 (Python Code)

Max Activating Token Index: 496

Text #15

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6302. Min Act: -0.0000

Data Index: 24556 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.5773. Min Act: -0.0000

Data Index: 479591 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6098. Min Act: -0.0000

Data Index: 79633 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.5529. Min Act: -0.0000

Data Index: 741789 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.5687. Min Act: -0.0000

Data Index: 1076094 (C4 (Web Text))

Max Activating Token Index: 808