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

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

Neuron 667 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.7098. Min Act: -0.0000

Data Index: 1625553 (Python Code)

Max Activating Token Index: 933

Text #1

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.8269. Min Act: -0.0000

Data Index: 1594591 (Python Code)

Max Activating Token Index: 611

Text #2

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.4602. Min Act: -0.0000

Data Index: 1508351 (Python Code)

Max Activating Token Index: 194

Text #3

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.6013. Min Act: -0.0000

Data Index: 1644100 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.6366. Min Act: -0.0000

Data Index: 1539622 (Python Code)

Max Activating Token Index: 439

Text #5

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.5277. Min Act: -0.0000

Data Index: 1401015 (Python Code)

Max Activating Token Index: 85

Text #6

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1414107 (Python Code)

Max Activating Token Index: 273

Text #7

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.5692. Min Act: -0.0000

Data Index: 1530797 (Python Code)

Max Activating Token Index: 491

Text #8

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3965. Min Act: -0.0000

Data Index: 1411593 (Python Code)

Max Activating Token Index: 248

Text #9

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.4533. Min Act: -0.0000

Data Index: 1475708 (Python Code)

Max Activating Token Index: 130

Text #10

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3391. Min Act: -0.0000

Data Index: 1382886 (Python Code)

Max Activating Token Index: 849

Text #11

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.2791. Min Act: -0.0000

Data Index: 1477902 (Python Code)

Max Activating Token Index: 335

Text #12

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.4868. Min Act: -0.0000

Data Index: 1378072 (Python Code)

Max Activating Token Index: 155

Text #13

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3324. Min Act: -0.0000

Data Index: 1491884 (Python Code)

Max Activating Token Index: 172

Text #14

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3523. Min Act: -0.0000

Data Index: 1433394 (Python Code)

Max Activating Token Index: 729

Text #15

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.4683. Min Act: -0.0000

Data Index: 1650406 (Python Code)

Max Activating Token Index: 265

Text #16

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3742. Min Act: -0.0000

Data Index: 1530774 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.2944. Min Act: -0.0000

Data Index: 1532774 (Python Code)

Max Activating Token Index: 600

Text #18

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3388. Min Act: -0.0000

Data Index: 1465330 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 1.8269. Min Range: -1.8269

Max Act: 1.3776. Min Act: -0.0000

Data Index: 1420777 (Python Code)

Max Activating Token Index: 621