Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1569 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.9147. Min Act: -0.0001

Data Index: 1465831 (Python Code)

Max Activating Token Index: 160

Text #1

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.9351. Min Act: -0.0001

Data Index: 1513721 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.9608. Min Act: -0.0001

Data Index: 1361739 (Python Code)

Max Activating Token Index: 586

Text #3

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.9592. Min Act: -0.0001

Data Index: 1592746 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.9019. Min Act: -0.0001

Data Index: 1624201 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.9086. Min Act: -0.0001

Data Index: 1652678 (Python Code)

Max Activating Token Index: 69

Text #6

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.8647. Min Act: -0.0001

Data Index: 1625403 (Python Code)

Max Activating Token Index: 960

Text #7

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.8580. Min Act: -0.0001

Data Index: 1405886 (Python Code)

Max Activating Token Index: 57

Text #8

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.8569. Min Act: -0.0001

Data Index: 1608057 (Python Code)

Max Activating Token Index: 34

Text #9

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.8806. Min Act: -0.0001

Data Index: 1466994 (Python Code)

Max Activating Token Index: 113

Text #10

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1360816 (Python Code)

Max Activating Token Index: 417

Text #11

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.8532. Min Act: -0.0001

Data Index: 1526356 (Python Code)

Max Activating Token Index: 64

Text #12

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.8197. Min Act: -0.0001

Data Index: 1552124 (Python Code)

Max Activating Token Index: 78

Text #13

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.8434. Min Act: -0.0001

Data Index: 1521879 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.8395. Min Act: -0.0001

Data Index: 1410907 (Python Code)

Max Activating Token Index: 932

Text #15

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.8353. Min Act: -0.0001

Data Index: 1515737 (Python Code)

Max Activating Token Index: 484

Text #16

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.9146. Min Act: -0.0001

Data Index: 1556243 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.8576. Min Act: -0.0001

Data Index: 1516392 (Python Code)

Max Activating Token Index: 521

Text #18

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.8851. Min Act: -0.0001

Data Index: 1477797 (Python Code)

Max Activating Token Index: 312

Text #19

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.8247. Min Act: -0.0001

Data Index: 1436295 (Python Code)

Max Activating Token Index: 32