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

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

Neuron 5064 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1130. Min Act: -0.0001

Data Index: 340637 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1084. Min Act: -0.0001

Data Index: 882288 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0975. Min Act: -0.0001

Data Index: 685954 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1249793 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1013. Min Act: -0.0001

Data Index: 188681 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0872. Min Act: -0.0001

Data Index: 813248 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0885. Min Act: -0.0001

Data Index: 710067 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0755. Min Act: -0.0001

Data Index: 159502 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0608. Min Act: -0.0001

Data Index: 359911 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0747. Min Act: -0.0001

Data Index: 636717 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0718. Min Act: -0.0001

Data Index: 524070 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0743. Min Act: -0.0001

Data Index: 269328 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0757. Min Act: -0.0001

Data Index: 1118314 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0702. Min Act: -0.0001

Data Index: 963809 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0617. Min Act: -0.0001

Data Index: 614247 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0629. Min Act: -0.0001

Data Index: 437199 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0675. Min Act: -0.0001

Data Index: 297245 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0720. Min Act: -0.0001

Data Index: 161190 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0569. Min Act: -0.0001

Data Index: 376444 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0736. Min Act: -0.0001

Data Index: 991029 (C4 (Web Text))

Max Activating Token Index: 715