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

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

Neuron 86 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: 0.0444. Min Range: -0.0444

Max Act: 0.0443. Min Act: -0.0003

Data Index: 407832 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0431. Min Act: -0.0002

Data Index: 385876 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0414. Min Act: -0.0003

Data Index: 582793 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0444. Min Act: -0.0002

Data Index: 748714 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1167407 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0420. Min Act: -0.0002

Data Index: 601479 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0431. Min Act: -0.0002

Data Index: 468710 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0412. Min Act: -0.0003

Data Index: 907903 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0435. Min Act: -0.0002

Data Index: 745280 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0426. Min Act: -0.0002

Data Index: 512283 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1215872 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0390. Min Act: -0.0002

Data Index: 740917 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0391. Min Act: -0.0002

Data Index: 432324 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1082757 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0329. Min Act: -0.0002

Data Index: 106013 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0318. Min Act: -0.0002

Data Index: 630843 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0310. Min Act: -0.0003

Data Index: 149211 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1242380 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1120936 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0285. Min Act: -0.0003

Data Index: 520296 (C4 (Web Text))

Max Activating Token Index: 689