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

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

Neuron 80 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1648528 (Python Code)

Max Activating Token Index: 656

Text #1

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1627316 (Python Code)

Max Activating Token Index: 688

Text #2

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1630976 (Python Code)

Max Activating Token Index: 33

Text #3

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1646709 (Python Code)

Max Activating Token Index: 498

Text #4

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1629049 (Python Code)

Max Activating Token Index: 277

Text #5

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1583074 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1509346 (Python Code)

Max Activating Token Index: 1005

Text #7

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1370753 (Python Code)

Max Activating Token Index: 564

Text #8

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1608122 (Python Code)

Max Activating Token Index: 768

Text #9

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1496397 (Python Code)

Max Activating Token Index: 759

Text #10

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0245. Min Act: -0.0002

Data Index: 363700 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1414043 (Python Code)

Max Activating Token Index: 332

Text #12

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1406715 (Python Code)

Max Activating Token Index: 374

Text #13

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1416720 (Python Code)

Max Activating Token Index: 217

Text #14

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1592010 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1652451 (Python Code)

Max Activating Token Index: 951

Text #16

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1455248 (Python Code)

Max Activating Token Index: 231

Text #17

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1433594 (Python Code)

Max Activating Token Index: 780

Text #18

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1413236 (Python Code)

Max Activating Token Index: 268

Text #19

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1401532 (Python Code)

Max Activating Token Index: 113