Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1707 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2743. Min Act: -0.0006

Data Index: 1507328 (Python Code)

Max Activating Token Index: 914

Text #1

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2825. Min Act: -0.0006

Data Index: 1592119 (Python Code)

Max Activating Token Index: 645

Text #2

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2800. Min Act: -0.0006

Data Index: 1507828 (Python Code)

Max Activating Token Index: 754

Text #3

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2286. Min Act: -0.0006

Data Index: 1449103 (Python Code)

Max Activating Token Index: 809

Text #4

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2377. Min Act: -0.0006

Data Index: 1473351 (Python Code)

Max Activating Token Index: 915

Text #5

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2319. Min Act: -0.0006

Data Index: 593933 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2309. Min Act: -0.0005

Data Index: 1469663 (Python Code)

Max Activating Token Index: 774

Text #7

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2037. Min Act: -0.0006

Data Index: 1476722 (Python Code)

Max Activating Token Index: 574

Text #8

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2132. Min Act: -0.0006

Data Index: 1451008 (Python Code)

Max Activating Token Index: 916

Text #9

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2173. Min Act: -0.0006

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1983. Min Act: -0.0006

Data Index: 1587485 (Python Code)

Max Activating Token Index: 588

Text #11

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1876. Min Act: -0.0006

Data Index: 1499970 (Python Code)

Max Activating Token Index: 713

Text #12

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1935. Min Act: -0.0006

Data Index: 1570421 (Python Code)

Max Activating Token Index: 554

Text #13

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1871. Min Act: -0.0006

Data Index: 557777 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1964. Min Act: -0.0006

Data Index: 1437924 (Python Code)

Max Activating Token Index: 698

Text #15

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1905. Min Act: -0.0006

Data Index: 1507842 (Python Code)

Max Activating Token Index: 603

Text #16

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1996. Min Act: -0.0006

Data Index: 1504280 (Python Code)

Max Activating Token Index: 102

Text #17

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1876. Min Act: -0.0006

Data Index: 1375545 (Python Code)

Max Activating Token Index: 640

Text #18

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1692. Min Act: -0.0006

Data Index: 1575383 (Python Code)

Max Activating Token Index: 866

Text #19

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1611. Min Act: -0.0006

Data Index: 1398214 (Python Code)

Max Activating Token Index: 971