Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2917 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1459017 (Python Code)

Max Activating Token Index: 671

Text #1

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2877. Min Act: -0.0000

Data Index: 383745 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1468283 (Python Code)

Max Activating Token Index: 913

Text #3

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1426564 (Python Code)

Max Activating Token Index: 880

Text #4

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1640426 (Python Code)

Max Activating Token Index: 626

Text #5

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2115. Min Act: -0.0000

Data Index: 731759 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2365. Min Act: -0.0000

Data Index: 727665 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1442275 (Python Code)

Max Activating Token Index: 157

Text #8

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2270. Min Act: -0.0000

Data Index: 605275 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2108. Min Act: -0.0000

Data Index: 862146 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.1980. Min Act: -0.0000

Data Index: 606145 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1432283 (Python Code)

Max Activating Token Index: 971

Text #12

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2057. Min Act: -0.0000

Data Index: 732234 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2088. Min Act: -0.0000

Data Index: 337969 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.1915. Min Act: -0.0000

Data Index: 301013 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2122. Min Act: -0.0000

Data Index: 553180 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1437493 (Python Code)

Max Activating Token Index: 954

Text #17

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.1871. Min Act: -0.0000

Data Index: 1348947 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1199605 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1243242 (C4 (Web Text))

Max Activating Token Index: 929