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

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

Neuron 3602 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2352. Min Act: -0.0000

Data Index: 896919 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2244. Min Act: -0.0000

Data Index: 208744 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2160. Min Act: -0.0000

Data Index: 609681 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2134. Min Act: -0.0000

Data Index: 503882 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1189136 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2069. Min Act: -0.0000

Data Index: 1330607 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2056. Min Act: -0.0000

Data Index: 658922 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1975. Min Act: -0.0000

Data Index: 453294 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1113062 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1996. Min Act: -0.0000

Data Index: 991104 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1980. Min Act: -0.0000

Data Index: 522447 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1924. Min Act: -0.0000

Data Index: 493516 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2003. Min Act: -0.0000

Data Index: 633573 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1908. Min Act: -0.0000

Data Index: 939502 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1331566 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1891. Min Act: -0.0000

Data Index: 846287 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1104165 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1858. Min Act: -0.0000

Data Index: 638408 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1075069 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1237103 (C4 (Web Text))

Max Activating Token Index: 662