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

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

Neuron 6120 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: 1.8728. Min Range: -1.8728

Max Act: 1.8728. Min Act: -0.0002

Data Index: 210509 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.7853. Min Act: -0.0002

Data Index: 795726 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.7512. Min Act: -0.0002

Data Index: 672639 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.7583. Min Act: -0.0002

Data Index: 814288 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.7059. Min Act: -0.0002

Data Index: 784429 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.6821. Min Act: -0.0002

Data Index: 712936 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.7018. Min Act: -0.0003

Data Index: 973784 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.7171. Min Act: -0.0002

Data Index: 1318751 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.6513. Min Act: -0.0002

Data Index: 758902 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.6237. Min Act: -0.0002

Data Index: 191091 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.6210. Min Act: -0.0002

Data Index: 1192943 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.5777. Min Act: -0.0003

Data Index: 740855 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.5715. Min Act: -0.0002

Data Index: 1031205 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.5765. Min Act: -0.0003

Data Index: 594432 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.6080. Min Act: -0.0002

Data Index: 508831 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.5912. Min Act: -0.0002

Data Index: 286061 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.5496. Min Act: -0.0002

Data Index: 291711 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.5252. Min Act: -0.0002

Data Index: 352333 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.5235. Min Act: -0.0002

Data Index: 864905 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 1.8728. Min Range: -1.8728

Max Act: 1.5773. Min Act: -0.0002

Data Index: 882068 (C4 (Web Text))

Max Activating Token Index: 761