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

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

Neuron 5272 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0740. Min Act: -0.0001

Data Index: 260032 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0825. Min Act: -0.0001

Data Index: 201522 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0786. Min Act: -0.0001

Data Index: 278216 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1187430 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0762. Min Act: -0.0002

Data Index: 56246 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0785. Min Act: -0.0001

Data Index: 870531 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0707. Min Act: -0.0001

Data Index: 670159 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0691. Min Act: -0.0002

Data Index: 922386 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0746. Min Act: -0.0001

Data Index: 323783 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0663. Min Act: -0.0002

Data Index: 232477 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1052998 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0684. Min Act: -0.0001

Data Index: 238020 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0663. Min Act: -0.0001

Data Index: 418367 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0828. Min Act: -0.0001

Data Index: 1309390 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0708. Min Act: -0.0001

Data Index: 836117 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1326019 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0633. Min Act: -0.0002

Data Index: 531175 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0727. Min Act: -0.0001

Data Index: 201113 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0635. Min Act: -0.0002

Data Index: 476617 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1089279 (C4 (Web Text))

Max Activating Token Index: 627