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

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

Neuron 1722 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: 2.3236. Min Range: -2.3236

Max Act: 2.2985. Min Act: -0.0000

Data Index: 1418632 (Python Code)

Max Activating Token Index: 709

Text #1

Max Range: 2.3236. Min Range: -2.3236

Max Act: 2.3236. Min Act: -0.0000

Data Index: 1454752 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 2.3236. Min Range: -2.3236

Max Act: 2.2717. Min Act: -0.0000

Data Index: 1475135 (Python Code)

Max Activating Token Index: 593

Text #3

Max Range: 2.3236. Min Range: -2.3236

Max Act: 2.2255. Min Act: -0.0000

Data Index: 1400317 (Python Code)

Max Activating Token Index: 855

Text #4

Max Range: 2.3236. Min Range: -2.3236

Max Act: 2.1828. Min Act: -0.0000

Data Index: 1493815 (Python Code)

Max Activating Token Index: 733

Text #5

Max Range: 2.3236. Min Range: -2.3236

Max Act: 2.0070. Min Act: -0.0000

Data Index: 1543459 (Python Code)

Max Activating Token Index: 161

Text #6

Max Range: 2.3236. Min Range: -2.3236

Max Act: 1.9002. Min Act: -0.0000

Data Index: 1588031 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 2.3236. Min Range: -2.3236

Max Act: 2.1057. Min Act: -0.0000

Data Index: 1619090 (Python Code)

Max Activating Token Index: 716

Text #8

Max Range: 2.3236. Min Range: -2.3236

Max Act: 1.9677. Min Act: -0.0000

Data Index: 1615750 (Python Code)

Max Activating Token Index: 139

Text #9

Max Range: 2.3236. Min Range: -2.3236

Max Act: 2.0728. Min Act: -0.0000

Data Index: 1625180 (Python Code)

Max Activating Token Index: 652

Text #10

Max Range: 2.3236. Min Range: -2.3236

Max Act: 2.0487. Min Act: -0.0000

Data Index: 1574879 (Python Code)

Max Activating Token Index: 689

Text #11

Max Range: 2.3236. Min Range: -2.3236

Max Act: 2.0245. Min Act: -0.0000

Data Index: 1445035 (Python Code)

Max Activating Token Index: 720

Text #12

Max Range: 2.3236. Min Range: -2.3236

Max Act: 2.0071. Min Act: -0.0000

Data Index: 1576011 (Python Code)

Max Activating Token Index: 571

Text #13

Max Range: 2.3236. Min Range: -2.3236

Max Act: 1.9714. Min Act: -0.0000

Data Index: 1592602 (Python Code)

Max Activating Token Index: 93

Text #14

Max Range: 2.3236. Min Range: -2.3236

Max Act: 1.9662. Min Act: -0.0000

Data Index: 73384 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 2.3236. Min Range: -2.3236

Max Act: 1.8396. Min Act: -0.0000

Data Index: 1390635 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 2.3236. Min Range: -2.3236

Max Act: 1.9254. Min Act: -0.0000

Data Index: 1546231 (Python Code)

Max Activating Token Index: 922

Text #17

Max Range: 2.3236. Min Range: -2.3236

Max Act: 1.8514. Min Act: -0.0000

Data Index: 1529159 (Python Code)

Max Activating Token Index: 907

Text #18

Max Range: 2.3236. Min Range: -2.3236

Max Act: 2.0187. Min Act: -0.0000

Data Index: 1449540 (Python Code)

Max Activating Token Index: 171

Text #19

Max Range: 2.3236. Min Range: -2.3236

Max Act: 1.8121. Min Act: -0.0000

Data Index: 1527482 (Python Code)

Max Activating Token Index: 506