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

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

Neuron 1701 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.9189. Min Act: -0.0001

Data Index: 1592278 (Python Code)

Max Activating Token Index: 723

Text #1

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.9220. Min Act: -0.0001

Data Index: 1481695 (Python Code)

Max Activating Token Index: 87

Text #2

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.8606. Min Act: -0.0001

Data Index: 1622397 (Python Code)

Max Activating Token Index: 973

Text #3

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1585132 (Python Code)

Max Activating Token Index: 646

Text #4

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.8242. Min Act: -0.0001

Data Index: 1362272 (Python Code)

Max Activating Token Index: 928

Text #5

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1423736 (Python Code)

Max Activating Token Index: 712

Text #6

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.8133. Min Act: -0.0000

Data Index: 1466697 (Python Code)

Max Activating Token Index: 897

Text #7

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7985. Min Act: -0.0001

Data Index: 1479131 (Python Code)

Max Activating Token Index: 125

Text #8

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.8235. Min Act: -0.0001

Data Index: 1646100 (Python Code)

Max Activating Token Index: 435

Text #9

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7723. Min Act: -0.0001

Data Index: 1444621 (Python Code)

Max Activating Token Index: 761

Text #10

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7792. Min Act: -0.0001

Data Index: 1496044 (Python Code)

Max Activating Token Index: 562

Text #11

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7976. Min Act: -0.0001

Data Index: 1467513 (Python Code)

Max Activating Token Index: 204

Text #12

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1469060 (Python Code)

Max Activating Token Index: 440

Text #13

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7435. Min Act: -0.0001

Data Index: 1495650 (Python Code)

Max Activating Token Index: 271

Text #14

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6959. Min Act: -0.0001

Data Index: 1633155 (Python Code)

Max Activating Token Index: 726

Text #15

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6964. Min Act: -0.0001

Data Index: 1372285 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1477595 (Python Code)

Max Activating Token Index: 659

Text #17

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7127. Min Act: -0.0001

Data Index: 1525625 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1471270 (Python Code)

Max Activating Token Index: 303

Text #19

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6765. Min Act: -0.0001

Data Index: 1506069 (Python Code)

Max Activating Token Index: 64