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

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

Neuron 632 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.5908. Min Act: -0.0001

Data Index: 954446 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.3869. Min Act: -0.0001

Data Index: 321811 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.2650. Min Act: -0.0001

Data Index: 932054 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.3234. Min Act: -0.0001

Data Index: 1086934 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.2287. Min Act: -0.0001

Data Index: 390809 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.2166. Min Act: -0.0001

Data Index: 164048 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.2622. Min Act: -0.0001

Data Index: 544188 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.2402. Min Act: -0.0001

Data Index: 574113 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.1691. Min Act: -0.0001

Data Index: 881768 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.1709. Min Act: -0.0001

Data Index: 33097 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.2706. Min Act: -0.0001

Data Index: 618905 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.2463. Min Act: -0.0001

Data Index: 884855 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.1370. Min Act: -0.0001

Data Index: 1238009 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.0820. Min Act: -0.0001

Data Index: 314656 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.3404. Min Act: -0.0001

Data Index: 1165447 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.1949. Min Act: -0.0001

Data Index: 386410 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.0238. Min Act: -0.0001

Data Index: 661155 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.1724. Min Act: -0.0001

Data Index: 290458 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.1121. Min Act: -0.0001

Data Index: 1092439 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 1.5908. Min Range: -1.5908

Max Act: 1.1264. Min Act: -0.0001

Data Index: 359144 (C4 (Web Text))

Max Activating Token Index: 851