Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1590 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1123644 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.3201. Min Act: -0.0001

Data Index: 1089291 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2720. Min Act: -0.0001

Data Index: 1226726 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2756. Min Act: -0.0001

Data Index: 140632 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2743. Min Act: -0.0000

Data Index: 163800 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2603. Min Act: -0.0000

Data Index: 901698 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2656. Min Act: -0.0000

Data Index: 810885 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2319. Min Act: -0.0000

Data Index: 228510 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2599. Min Act: -0.0000

Data Index: 705067 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2789. Min Act: -0.0001

Data Index: 693320 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2498. Min Act: -0.0001

Data Index: 48119 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2383. Min Act: -0.0001

Data Index: 594552 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1091284 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2350. Min Act: -0.0000

Data Index: 409808 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2377. Min Act: -0.0001

Data Index: 579323 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2298. Min Act: -0.0001

Data Index: 147404 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2110. Min Act: -0.0001

Data Index: 1139066 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1004057 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1028742 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.3308. Min Range: -0.3308

Max Act: 0.2392. Min Act: -0.0000

Data Index: 703999 (C4 (Web Text))

Max Activating Token Index: 747