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

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

Neuron 4640 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0500. Min Act: -0.0003

Data Index: 693802 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0002

Data Index: 320358 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0504. Min Act: -0.0002

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0480. Min Act: -0.0003

Data Index: 549566 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1246204 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0456. Min Act: -0.0003

Data Index: 95061 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0461. Min Act: -0.0003

Data Index: 16857 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1072016 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0435. Min Act: -0.0002

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1088467 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0442. Min Act: -0.0002

Data Index: 300431 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0412. Min Act: -0.0003

Data Index: 216553 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0414. Min Act: -0.0003

Data Index: 277824 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0412. Min Act: -0.0002

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0428. Min Act: -0.0003

Data Index: 140512 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0417. Min Act: -0.0003

Data Index: 837357 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0436. Min Act: -0.0003

Data Index: 3248 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0408. Min Act: -0.0003

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1195066 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0378. Min Act: -0.0003

Data Index: 680953 (C4 (Web Text))

Max Activating Token Index: 360