Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1924 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0631. Min Act: -0.0001

Data Index: 736956 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1213946 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1122847 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0616. Min Act: -0.0002

Data Index: 290733 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0574. Min Act: -0.0001

Data Index: 1209333 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0595. Min Act: -0.0002

Data Index: 858208 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0583. Min Act: -0.0001

Data Index: 386163 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0590. Min Act: -0.0001

Data Index: 370652 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0563. Min Act: -0.0002

Data Index: 229958 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1094146 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0566. Min Act: -0.0001

Data Index: 641143 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0564. Min Act: -0.0002

Data Index: 298155 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0556. Min Act: -0.0002

Data Index: 241416 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1228297 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1228182 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1305457 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0559. Min Act: -0.0001

Data Index: 349336 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0549. Min Act: -0.0001

Data Index: 843584 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0546. Min Act: -0.0002

Data Index: 574042 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0534. Min Act: -0.0001

Data Index: 566524 (C4 (Web Text))

Max Activating Token Index: 510