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

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

Neuron 5477 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: 0.0653. Min Range: -0.0653

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1137241 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0623. Min Act: -0.0002

Data Index: 879542 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0592. Min Act: -0.0002

Data Index: 499221 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1043795 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0569. Min Act: -0.0002

Data Index: 178095 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0573. Min Act: -0.0002

Data Index: 26410 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0577. Min Act: -0.0002

Data Index: 370259 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0564. Min Act: -0.0002

Data Index: 785722 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1123983 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0553. Min Act: -0.0002

Data Index: 380295 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0550. Min Act: -0.0002

Data Index: 354658 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0546. Min Act: -0.0002

Data Index: 93178 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1284733 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0521. Min Act: -0.0002

Data Index: 52204 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0518. Min Act: -0.0002

Data Index: 510256 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0522. Min Act: -0.0002

Data Index: 430686 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0519. Min Act: -0.0002

Data Index: 685315 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0520. Min Act: -0.0002

Data Index: 866572 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1216766 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1255059 (C4 (Web Text))

Max Activating Token Index: 35