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

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

Neuron 1005 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2539. Min Act: -0.0001

Data Index: 344857 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.2262. Min Act: -0.0001

Data Index: 1117334 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1884. Min Act: -0.0001

Data Index: 46091 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1873. Min Act: -0.0001

Data Index: 586987 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1905. Min Act: -0.0001

Data Index: 741337 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1809. Min Act: -0.0001

Data Index: 284107 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1752. Min Act: -0.0001

Data Index: 1023299 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1706. Min Act: -0.0001

Data Index: 26649 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1641. Min Act: -0.0001

Data Index: 1337006 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1718. Min Act: -0.0001

Data Index: 688258 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1743. Min Act: -0.0001

Data Index: 589003 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1244443 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1640. Min Act: -0.0001

Data Index: 1209041 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1485. Min Act: -0.0001

Data Index: 1268050 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1553. Min Act: -0.0001

Data Index: 848943 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1580. Min Act: -0.0001

Data Index: 123073 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1575. Min Act: -0.0001

Data Index: 410246 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1519. Min Act: -0.0001

Data Index: 844703 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1556. Min Act: -0.0001

Data Index: 731744 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.2539. Min Range: -0.2539

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1300755 (C4 (Web Text))

Max Activating Token Index: 924