Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2707 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1327406 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1041791 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1208817 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4317. Min Act: -0.0000

Data Index: 774512 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4541. Min Act: -0.0000

Data Index: 195235 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4223. Min Act: -0.0000

Data Index: 252160 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4104. Min Act: -0.0000

Data Index: 265846 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1024861 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1627900 (Python Code)

Max Activating Token Index: 78

Text #9

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1561328 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1463872 (Python Code)

Max Activating Token Index: 85

Text #11

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1407253 (Python Code)

Max Activating Token Index: 652

Text #12

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1391312 (Python Code)

Max Activating Token Index: 907

Text #13

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1429541 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1398032 (Python Code)

Max Activating Token Index: 777

Text #15

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1520029 (Python Code)

Max Activating Token Index: 81

Text #16

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.3619. Min Act: -0.0000

Data Index: 1387688 (Python Code)

Max Activating Token Index: 890

Text #17

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.3736. Min Act: 0.0000

Data Index: 112272 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.3722. Min Act: -0.0000

Data Index: 646494 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1616901 (Python Code)

Max Activating Token Index: 782