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

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

Neuron 4753 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1187. Min Act: -0.0002

Data Index: 193055 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0995. Min Act: -0.0002

Data Index: 88799 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1148. Min Act: -0.0002

Data Index: 1177309 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1003. Min Act: -0.0002

Data Index: 573968 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0972. Min Act: -0.0002

Data Index: 533134 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0946. Min Act: -0.0002

Data Index: 607318 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1064. Min Act: -0.0002

Data Index: 654013 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0916. Min Act: -0.0002

Data Index: 416225 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0999. Min Act: -0.0002

Data Index: 518306 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1101905 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0916. Min Act: -0.0002

Data Index: 225806 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0953. Min Act: -0.0002

Data Index: 31954 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0867. Min Act: -0.0002

Data Index: 763838 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0856. Min Act: -0.0002

Data Index: 569058 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1296966 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0875. Min Act: -0.0002

Data Index: 535902 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0936. Min Act: -0.0002

Data Index: 629096 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0838. Min Act: -0.0002

Data Index: 793499 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1011844 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0864. Min Act: -0.0002

Data Index: 375560 (C4 (Web Text))

Max Activating Token Index: 42