Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2785 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1507. Min Act: -0.0001

Data Index: 567555 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1540. Min Act: -0.0001

Data Index: 961189 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1357. Min Act: -0.0001

Data Index: 245317 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1296. Min Act: -0.0001

Data Index: 757508 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1220. Min Act: -0.0001

Data Index: 397738 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1099. Min Act: -0.0001

Data Index: 746105 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1180. Min Act: -0.0001

Data Index: 936699 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1204. Min Act: -0.0001

Data Index: 218072 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1075. Min Act: -0.0001

Data Index: 907673 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1283627 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1087. Min Act: -0.0001

Data Index: 201214 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1088. Min Act: -0.0001

Data Index: 252298 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.0927. Min Act: -0.0001

Data Index: 899244 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.0982. Min Act: -0.0001

Data Index: 71725 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1147520 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1300592 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1001. Min Act: -0.0001

Data Index: 699263 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.0985. Min Act: -0.0001

Data Index: 871216 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1038. Min Act: -0.0001

Data Index: 381368 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.0954. Min Act: -0.0001

Data Index: 254817 (C4 (Web Text))

Max Activating Token Index: 937