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

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

Neuron 4905 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.2183. Min Act: -0.0003

Data Index: 830282 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.2152. Min Act: -0.0003

Data Index: 104830 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.2121. Min Act: -0.0003

Data Index: 1035647 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.2035. Min Act: -0.0003

Data Index: 80316 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.2041. Min Act: -0.0003

Data Index: 706617 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1963. Min Act: -0.0003

Data Index: 1142660 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.2010. Min Act: -0.0003

Data Index: 600200 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1969. Min Act: -0.0003

Data Index: 435214 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1938. Min Act: -0.0003

Data Index: 14141 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1941. Min Act: -0.0003

Data Index: 1158478 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1909. Min Act: -0.0003

Data Index: 875287 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1881. Min Act: -0.0003

Data Index: 136201 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1869. Min Act: -0.0003

Data Index: 53352 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1914. Min Act: -0.0003

Data Index: 1192853 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1843. Min Act: -0.0003

Data Index: 1339363 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1844. Min Act: -0.0003

Data Index: 377453 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1902. Min Act: -0.0003

Data Index: 1354100 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1827. Min Act: -0.0003

Data Index: 1069677 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1804. Min Act: -0.0003

Data Index: 1157789 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.2183. Min Range: -0.2183

Max Act: 0.1753. Min Act: -0.0003

Data Index: 499802 (C4 (Web Text))

Max Activating Token Index: 640