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

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

Neuron 1406 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1572. Min Act: -0.0000

Data Index: 461056 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0098. Min Act: -0.0000

Data Index: 1214737 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1365. Min Act: -0.0000

Data Index: 123181 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0120. Min Act: -0.0000

Data Index: 756103 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0488. Min Act: -0.0000

Data Index: 83093 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0434. Min Act: -0.0000

Data Index: 760724 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0394. Min Act: -0.0000

Data Index: 96366 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0405. Min Act: -0.0000

Data Index: 950728 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0380. Min Act: -0.0000

Data Index: 641302 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0372. Min Act: -0.0000

Data Index: 557826 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0381. Min Act: -0.0000

Data Index: 752652 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0360. Min Act: -0.0000

Data Index: 751679 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0348. Min Act: -0.0000

Data Index: 298791 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0331. Min Act: -0.0000

Data Index: 945518 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0351. Min Act: -0.0000

Data Index: 535113 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0350. Min Act: -0.0000

Data Index: 188033 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1134452 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0361. Min Act: -0.0000

Data Index: 894542 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0325. Min Act: -0.0000

Data Index: 493581 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0337. Min Act: -0.0000

Data Index: 781780 (C4 (Web Text))

Max Activating Token Index: 302