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

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

Neuron 4791 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: 0.7194. Min Range: -0.7194

Max Act: 0.7099. Min Act: -0.0001

Data Index: 1177314 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.7194. Min Act: -0.0001

Data Index: 498145 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.7073. Min Act: -0.0001

Data Index: 1015695 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6957. Min Act: -0.0001

Data Index: 135252 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6376. Min Act: -0.0001

Data Index: 1623288 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6697. Min Act: -0.0001

Data Index: 590711 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6419. Min Act: -0.0001

Data Index: 1539538 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6247. Min Act: -0.0001

Data Index: 1654700 (Python Code)

Max Activating Token Index: 801

Text #8

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6208. Min Act: -0.0001

Data Index: 1504288 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6187. Min Act: -0.0001

Data Index: 1472280 (Python Code)

Max Activating Token Index: 44

Text #10

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6410. Min Act: -0.0001

Data Index: 1634082 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5963. Min Act: -0.0001

Data Index: 1519068 (Python Code)

Max Activating Token Index: 62

Text #12

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5789. Min Act: -0.0001

Data Index: 1416293 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5981. Min Act: -0.0001

Data Index: 1593550 (Python Code)

Max Activating Token Index: 70

Text #14

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5981. Min Act: -0.0001

Data Index: 1627477 (Python Code)

Max Activating Token Index: 70

Text #15

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5656. Min Act: -0.0001

Data Index: 1634573 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6041. Min Act: -0.0001

Data Index: 1566632 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6032. Min Act: -0.0001

Data Index: 1375214 (Python Code)

Max Activating Token Index: 66

Text #18

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6000. Min Act: -0.0001

Data Index: 1452987 (Python Code)

Max Activating Token Index: 45

Text #19

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5998. Min Act: -0.0001

Data Index: 1461544 (Python Code)

Max Activating Token Index: 46