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

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

Neuron 2156 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9541. Min Range: -1.9541

Max Act: 1.9541. Min Act: -0.0002

Data Index: 1156742 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 1.9541. Min Range: -1.9541

Max Act: 1.7288. Min Act: -0.0002

Data Index: 1157896 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 1.9541. Min Range: -1.9541

Max Act: 1.1774. Min Act: -0.0003

Data Index: 470865 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 1.9541. Min Range: -1.9541

Max Act: 1.0495. Min Act: -0.0003

Data Index: 1185417 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 1.9541. Min Range: -1.9541

Max Act: 1.1361. Min Act: -0.0003

Data Index: 1250913 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.9541. Min Range: -1.9541

Max Act: 1.0549. Min Act: -0.0002

Data Index: 933128 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 1.9541. Min Range: -1.9541

Max Act: 1.0162. Min Act: -0.0003

Data Index: 1157814 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 1.9541. Min Range: -1.9541

Max Act: 0.9743. Min Act: -0.0003

Data Index: 1201796 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 1.9541. Min Range: -1.9541

Max Act: 0.9401. Min Act: -0.0003

Data Index: 1322950 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 1.9541. Min Range: -1.9541

Max Act: 0.9716. Min Act: -0.0003

Data Index: 357998 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 1.9541. Min Range: -1.9541

Max Act: 0.9602. Min Act: -0.0003

Data Index: 387492 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 1.9541. Min Range: -1.9541

Max Act: 0.9123. Min Act: -0.0003

Data Index: 539265 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 1.9541. Min Range: -1.9541

Max Act: 0.8478. Min Act: -0.0003

Data Index: 790125 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 1.9541. Min Range: -1.9541

Max Act: 0.8767. Min Act: -0.0002

Data Index: 217178 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 1.9541. Min Range: -1.9541

Max Act: 0.8466. Min Act: -0.0003

Data Index: 279323 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 1.9541. Min Range: -1.9541

Max Act: 0.8878. Min Act: -0.0002

Data Index: 1162891 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 1.9541. Min Range: -1.9541

Max Act: 0.8988. Min Act: -0.0003

Data Index: 1107582 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 1.9541. Min Range: -1.9541

Max Act: 0.8209. Min Act: -0.0002

Data Index: 1138770 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 1.9541. Min Range: -1.9541

Max Act: 0.8505. Min Act: -0.0003

Data Index: 8164 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 1.9541. Min Range: -1.9541

Max Act: 0.9270. Min Act: -0.0002

Data Index: 1318403 (C4 (Web Text))

Max Activating Token Index: 74