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

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

Neuron 1116 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0601. Min Act: -0.0000

Data Index: 657228 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0677. Min Act: -0.0000

Data Index: 182753 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1302744 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0592. Min Act: -0.0000

Data Index: 938836 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0552. Min Act: -0.0000

Data Index: 1050516 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0546. Min Act: -0.0000

Data Index: 1070174 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0510. Min Act: -0.0000

Data Index: 295942 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0552. Min Act: -0.0000

Data Index: 1190219 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0511. Min Act: -0.0000

Data Index: 1144612 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1129519 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0492. Min Act: -0.0001

Data Index: 976855 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0532. Min Act: -0.0000

Data Index: 905666 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0529. Min Act: -0.0000

Data Index: 913087 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0511. Min Act: -0.0000

Data Index: 453901 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0506. Min Act: -0.0000

Data Index: 995552 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0526. Min Act: -0.0000

Data Index: 394715 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0516. Min Act: -0.0000

Data Index: 769799 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1101923 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0477. Min Act: -0.0000

Data Index: 981654 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0491. Min Act: -0.0000

Data Index: 1056118 (C4 (Web Text))

Max Activating Token Index: 278