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

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

Neuron 3980 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2250. Min Act: -0.0000

Data Index: 267081 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1967. Min Act: -0.0000

Data Index: 892777 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1933. Min Act: -0.0000

Data Index: 620039 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1307721 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1351433 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1122219 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1270826 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1143014 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1249074 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1892. Min Act: -0.0000

Data Index: 990553 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1895. Min Act: -0.0000

Data Index: 912561 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1762. Min Act: -0.0000

Data Index: 690511 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1854. Min Act: -0.0000

Data Index: 645010 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1858. Min Act: -0.0000

Data Index: 755222 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1657. Min Act: -0.0000

Data Index: 968819 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1249523 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1827. Min Act: -0.0000

Data Index: 457342 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1074649 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1729. Min Act: -0.0000

Data Index: 633959 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1702. Min Act: -0.0000

Data Index: 170823 (C4 (Web Text))

Max Activating Token Index: 786