Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1003 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0475. Min Act: -0.0002

Data Index: 48845 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0469. Min Act: -0.0003

Data Index: 815257 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0426. Min Act: -0.0002

Data Index: 458722 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1111649 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0407. Min Act: -0.0002

Data Index: 273990 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0421. Min Act: -0.0001

Data Index: 833884 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1068604 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0415. Min Act: -0.0003

Data Index: 749690 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0413. Min Act: -0.0003

Data Index: 457500 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0416. Min Act: -0.0003

Data Index: 3058 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0415. Min Act: -0.0003

Data Index: 449953 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0413. Min Act: -0.0004

Data Index: 182484 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1346077 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0395. Min Act: -0.0003

Data Index: 948441 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0385. Min Act: -0.0003

Data Index: 969671 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0383. Min Act: -0.0003

Data Index: 794211 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0386. Min Act: -0.0002

Data Index: 276183 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0383. Min Act: -0.0002

Data Index: 147179 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0378. Min Act: -0.0002

Data Index: 216790 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0378. Min Act: -0.0003

Data Index: 270351 (C4 (Web Text))

Max Activating Token Index: 971