Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 814 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0469. Min Act: -0.0004

Data Index: 706440 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0460. Min Act: -0.0004

Data Index: 423870 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0004

Data Index: 426116 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0449. Min Act: -0.0004

Data Index: 942671 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0431. Min Act: -0.0004

Data Index: 944180 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0394. Min Act: -0.0004

Data Index: 134325 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0420. Min Act: -0.0004

Data Index: 1150154 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0418. Min Act: -0.0004

Data Index: 371762 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0430. Min Act: -0.0004

Data Index: 1283572 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0414. Min Act: -0.0004

Data Index: 231856 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0414. Min Act: -0.0004

Data Index: 991778 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0414. Min Act: -0.0004

Data Index: 156698 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0397. Min Act: -0.0004

Data Index: 169985 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0414. Min Act: -0.0004

Data Index: 737986 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0405. Min Act: -0.0004

Data Index: 944495 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0440. Min Act: -0.0004

Data Index: 900763 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0401. Min Act: -0.0004

Data Index: 515780 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0385. Min Act: -0.0004

Data Index: 932610 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0401. Min Act: -0.0004

Data Index: 873552 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0417. Min Act: -0.0004

Data Index: 1196899 (C4 (Web Text))

Max Activating Token Index: 104