Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 590 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1174922 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0538. Min Act: -0.0002

Data Index: 488502 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0511. Min Act: -0.0002

Data Index: 270505 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0513. Min Act: -0.0003

Data Index: 161432 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0474. Min Act: -0.0004

Data Index: 1229238 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1295865 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0475. Min Act: -0.0003

Data Index: 978899 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0499. Min Act: -0.0003

Data Index: 614336 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0497. Min Act: -0.0003

Data Index: 212901 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1066437 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0487. Min Act: -0.0003

Data Index: 204399 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0480. Min Act: -0.0003

Data Index: 931593 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0478. Min Act: -0.0003

Data Index: 756770 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1077963 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0479. Min Act: -0.0002

Data Index: 978506 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0472. Min Act: -0.0002

Data Index: 397992 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0444. Min Act: -0.0003

Data Index: 710458 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0458. Min Act: -0.0003

Data Index: 863736 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0456. Min Act: -0.0003

Data Index: 899804 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0439. Min Act: -0.0003

Data Index: 449395 (C4 (Web Text))

Max Activating Token Index: 566