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

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

Neuron 4659 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1196384 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1081. Min Act: -0.0002

Data Index: 535031 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1015. Min Act: -0.0002

Data Index: 914777 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0987. Min Act: -0.0002

Data Index: 1626103 (Python Code)

Max Activating Token Index: 744

Text #4

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0959. Min Act: -0.0002

Data Index: 432798 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0962. Min Act: -0.0002

Data Index: 244268 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0914. Min Act: -0.0002

Data Index: 824749 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0880. Min Act: -0.0002

Data Index: 281040 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0891. Min Act: -0.0002

Data Index: 117399 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0890. Min Act: -0.0002

Data Index: 417133 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0858. Min Act: -0.0002

Data Index: 176638 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0856. Min Act: -0.0002

Data Index: 702830 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0846. Min Act: -0.0002

Data Index: 849210 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0870. Min Act: -0.0002

Data Index: 717215 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1053620 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0857. Min Act: -0.0002

Data Index: 577841 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1516913 (Python Code)

Max Activating Token Index: 457

Text #17

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1274877 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0841. Min Act: -0.0002

Data Index: 569728 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0818. Min Act: -0.0002

Data Index: 283851 (C4 (Web Text))

Max Activating Token Index: 228