Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2439 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.2653. Min Act: -0.0001

Data Index: 1252939 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.2147. Min Act: -0.0001

Data Index: 101144 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.2217. Min Act: -0.0001

Data Index: 148930 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1956. Min Act: -0.0000

Data Index: 912970 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1305463 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1862. Min Act: -0.0001

Data Index: 898891 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1832. Min Act: -0.0001

Data Index: 206962 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1836. Min Act: -0.0001

Data Index: 572823 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1695. Min Act: -0.0001

Data Index: 734663 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1325065 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1945. Min Act: -0.0001

Data Index: 923796 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1652. Min Act: -0.0001

Data Index: 1275392 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1716. Min Act: -0.0001

Data Index: 144943 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1707. Min Act: -0.0001

Data Index: 275199 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1694. Min Act: -0.0001

Data Index: 346405 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1710. Min Act: -0.0001

Data Index: 538955 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1577. Min Act: -0.0001

Data Index: 1133740 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1799. Min Act: -0.0001

Data Index: 1045419 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1679. Min Act: -0.0001

Data Index: 1300341 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1746. Min Act: -0.0001

Data Index: 59551 (C4 (Web Text))

Max Activating Token Index: 532