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

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

Neuron 4797 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: 0.0709. Min Range: -0.0709

Max Act: 0.0709. Min Act: -0.0003

Data Index: 274418 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0673. Min Act: -0.0002

Data Index: 855904 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1275590 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0617. Min Act: -0.0002

Data Index: 62202 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0569. Min Act: -0.0002

Data Index: 283954 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1126674 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0623. Min Act: -0.0003

Data Index: 927259 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1123773 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0598. Min Act: -0.0002

Data Index: 807045 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0598. Min Act: -0.0002

Data Index: 499092 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0539. Min Act: -0.0002

Data Index: 405668 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0552. Min Act: -0.0002

Data Index: 552309 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0584. Min Act: -0.0002

Data Index: 939577 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0520. Min Act: -0.0002

Data Index: 187650 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0635. Min Act: -0.0002

Data Index: 924346 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0586. Min Act: -0.0003

Data Index: 671442 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0546. Min Act: -0.0002

Data Index: 597168 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1171050 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0561. Min Act: -0.0002

Data Index: 470103 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0593. Min Act: -0.0002

Data Index: 201923 (C4 (Web Text))

Max Activating Token Index: 450