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

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

Neuron 1704 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0988. Min Act: -0.0002

Data Index: 681999 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0791. Min Act: -0.0002

Data Index: 350976 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0819. Min Act: -0.0002

Data Index: 614559 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0807. Min Act: -0.0002

Data Index: 552282 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0865. Min Act: -0.0002

Data Index: 236560 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0772. Min Act: -0.0002

Data Index: 807478 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0793. Min Act: -0.0002

Data Index: 303021 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0773. Min Act: -0.0002

Data Index: 361059 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1089215 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0773. Min Act: -0.0002

Data Index: 296576 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0784. Min Act: -0.0002

Data Index: 557361 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0795. Min Act: -0.0002

Data Index: 233626 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0731. Min Act: -0.0002

Data Index: 231889 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0775. Min Act: -0.0002

Data Index: 10092 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0746. Min Act: -0.0002

Data Index: 148355 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0772. Min Act: -0.0002

Data Index: 377242 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0745. Min Act: -0.0002

Data Index: 319160 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0736. Min Act: -0.0002

Data Index: 709044 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0787. Min Act: -0.0002

Data Index: 547987 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0741. Min Act: -0.0002

Data Index: 875633 (C4 (Web Text))

Max Activating Token Index: 499