Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4271 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0556. Min Act: -0.0002

Data Index: 183391 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1630387 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1466775 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1525438 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1593221 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1566868 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1559479 (Python Code)

Max Activating Token Index: 736

Text #7

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1563494 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1412477 (Python Code)

Max Activating Token Index: 225

Text #9

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1546300 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1656716 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1648617 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1579379 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1435520 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1504544 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1365107 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1400084 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1373990 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1477720 (Python Code)

Max Activating Token Index: 117

Text #19

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1498654 (Python Code)

Max Activating Token Index: 7