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

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

Neuron 3504 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1484971 (Python Code)

Max Activating Token Index: 1020

Text #1

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1374360 (Python Code)

Max Activating Token Index: 323

Text #2

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1369509 (Python Code)

Max Activating Token Index: 848

Text #3

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1394198 (Python Code)

Max Activating Token Index: 100

Text #4

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1459045 (Python Code)

Max Activating Token Index: 356

Text #5

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1516225 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1642201 (Python Code)

Max Activating Token Index: 364

Text #7

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1537884 (Python Code)

Max Activating Token Index: 160

Text #8

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1555388 (Python Code)

Max Activating Token Index: 67

Text #9

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1550011 (Python Code)

Max Activating Token Index: 215

Text #10

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1544264 (Python Code)

Max Activating Token Index: 339

Text #11

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1407567 (Python Code)

Max Activating Token Index: 478

Text #12

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1500707 (Python Code)

Max Activating Token Index: 147

Text #13

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1443777 (Python Code)

Max Activating Token Index: 229

Text #14

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1496011 (Python Code)

Max Activating Token Index: 344

Text #15

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1572922 (Python Code)

Max Activating Token Index: 71

Text #16

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1649062 (Python Code)

Max Activating Token Index: 374

Text #17

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1650762 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1637970 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 0.6368. Min Range: -0.6368

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1362759 (Python Code)

Max Activating Token Index: 289