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

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

Neuron 1915 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: 0.4247. Min Range: -0.4247

Max Act: 0.4247. Min Act: -0.0000

Data Index: 784783 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3967. Min Act: -0.0001

Data Index: 347880 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3837. Min Act: -0.0000

Data Index: 971452 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3615. Min Act: -0.0000

Data Index: 455744 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.3348. Min Act: -0.0001

Data Index: 1123571 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2935. Min Act: -0.0000

Data Index: 831374 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2257. Min Act: -0.0000

Data Index: 604903 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2243. Min Act: -0.0000

Data Index: 604600 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2093. Min Act: -0.0000

Data Index: 857554 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2091. Min Act: -0.0001

Data Index: 302936 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2083. Min Act: -0.0000

Data Index: 572806 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.1800. Min Act: -0.0001

Data Index: 221902 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2074. Min Act: -0.0000

Data Index: 940165 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.1862. Min Act: -0.0001

Data Index: 79611 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.1894. Min Act: -0.0000

Data Index: 707913 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.1812. Min Act: -0.0001

Data Index: 942972 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.1927. Min Act: -0.0000

Data Index: 135904 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.1859. Min Act: -0.0000

Data Index: 113063 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.1567. Min Act: -0.0000

Data Index: 628637 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.1836. Min Act: -0.0000

Data Index: 295292 (C4 (Web Text))

Max Activating Token Index: 961