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

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

Neuron 1435 in Layer 0

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: 0.0638. Min Range: -0.0638

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1351528 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1338408 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0576. Min Act: -0.0001

Data Index: 820006 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0558. Min Act: -0.0001

Data Index: 719145 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0558. Min Act: -0.0001

Data Index: 894035 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0553. Min Act: -0.0001

Data Index: 1059265 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0541. Min Act: -0.0001

Data Index: 86308 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0521. Min Act: -0.0001

Data Index: 724546 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1003946 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0520. Min Act: -0.0001

Data Index: 893239 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0522. Min Act: -0.0001

Data Index: 896809 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0530. Min Act: -0.0001

Data Index: 658388 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0520. Min Act: -0.0001

Data Index: 397258 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1329517 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0500. Min Act: -0.0001

Data Index: 159830 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0501. Min Act: -0.0001

Data Index: 1584016 (Python Code)

Max Activating Token Index: 64

Text #16

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1137804 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0504. Min Act: -0.0001

Data Index: 559109 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0492. Min Act: -0.0001

Data Index: 788691 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0504. Min Act: -0.0001

Data Index: 595636 (C4 (Web Text))

Max Activating Token Index: 802