Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 132 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1830. Min Range: -2.1830

Max Act: 2.1830. Min Act: -0.0000

Data Index: 997991 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 2.1830. Min Range: -2.1830

Max Act: 2.0418. Min Act: -0.0000

Data Index: 103627 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 2.1830. Min Range: -2.1830

Max Act: 1.2256. Min Act: -0.0000

Data Index: 325900 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 2.1830. Min Range: -2.1830

Max Act: 1.1607. Min Act: -0.0000

Data Index: 971294 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.9252. Min Act: -0.0000

Data Index: 134777 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1245491 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.8372. Min Act: -0.0000

Data Index: 514263 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.8082. Min Act: -0.0000

Data Index: 283828 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1070739 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.7286. Min Act: -0.0000

Data Index: 102040 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.7636. Min Act: -0.0000

Data Index: 817175 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.7713. Min Act: -0.0000

Data Index: 317149 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.7999. Min Act: -0.0000

Data Index: 856754 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.7321. Min Act: -0.0000

Data Index: 512926 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.7042. Min Act: -0.0000

Data Index: 37753 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.6768. Min Act: 0.0000

Data Index: 614860 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.7149. Min Act: -0.0000

Data Index: 908040 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1052819 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.6877. Min Act: -0.0000

Data Index: 167362 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 2.1830. Min Range: -2.1830

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1025866 (C4 (Web Text))

Max Activating Token Index: 474