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

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

Neuron 808 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1106. Min Act: -0.0001

Data Index: 552344 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1562595 (Python Code)

Max Activating Token Index: 29

Text #2

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1430215 (Python Code)

Max Activating Token Index: 610

Text #3

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0919. Min Act: -0.0001

Data Index: 888059 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1254664 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1536653 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1028712 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1194286 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0846. Min Act: -0.0001

Data Index: 359068 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0847. Min Act: -0.0000

Data Index: 265212 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1623655 (Python Code)

Max Activating Token Index: 801

Text #11

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1347929 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1374215 (Python Code)

Max Activating Token Index: 877

Text #13

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0827. Min Act: -0.0000

Data Index: 237988 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1418235 (Python Code)

Max Activating Token Index: 167

Text #15

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0757. Min Act: -0.0001

Data Index: 1477573 (Python Code)

Max Activating Token Index: 48

Text #16

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1315307 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1464341 (Python Code)

Max Activating Token Index: 195

Text #18

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1007758 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1588954 (Python Code)

Max Activating Token Index: 1011