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

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

Neuron 4823 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1568. Min Range: -1.1568

Max Act: 1.1423. Min Act: -0.0000

Data Index: 920358 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 1.1568. Min Range: -1.1568

Max Act: 1.1224. Min Act: -0.0000

Data Index: 840512 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 1.1568. Min Range: -1.1568

Max Act: 1.1568. Min Act: -0.0000

Data Index: 366068 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 1.1568. Min Range: -1.1568

Max Act: 1.0319. Min Act: -0.0000

Data Index: 796867 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 1.1568. Min Range: -1.1568

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1138771 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.1568. Min Range: -1.1568

Max Act: 1.0769. Min Act: -0.0000

Data Index: 860750 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.9300. Min Act: -0.0000

Data Index: 403010 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.9866. Min Act: -0.0000

Data Index: 644432 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1249114 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.8615. Min Act: -0.0000

Data Index: 591028 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1057967 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.8430. Min Act: -0.0000

Data Index: 58471 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.8671. Min Act: -0.0000

Data Index: 222650 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.8510. Min Act: -0.0000

Data Index: 349447 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.8431. Min Act: -0.0000

Data Index: 276610 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.8357. Min Act: -0.0000

Data Index: 810967 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.7619. Min Act: -0.0000

Data Index: 200707 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.7926. Min Act: -0.0000

Data Index: 934218 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.7234. Min Act: -0.0000

Data Index: 99611 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 1.1568. Min Range: -1.1568

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1330441 (C4 (Web Text))

Max Activating Token Index: 479