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

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

Neuron 4113 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0093. Min Range: -1.0093

Max Act: 1.0093. Min Act: -0.0000

Data Index: 460932 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.9234. Min Act: -0.0000

Data Index: 952652 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8345. Min Act: -0.0000

Data Index: 952559 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7579. Min Act: -0.0000

Data Index: 239072 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7222. Min Act: -0.0001

Data Index: 508855 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1090656 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7373. Min Act: -0.0000

Data Index: 717969 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6703. Min Act: -0.0000

Data Index: 620631 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6982. Min Act: -0.0000

Data Index: 545876 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1316938 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6508. Min Act: -0.0000

Data Index: 435642 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6777. Min Act: -0.0000

Data Index: 862869 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1311505 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1033232 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6393. Min Act: -0.0001

Data Index: 984373 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6546. Min Act: -0.0000

Data Index: 363206 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5984. Min Act: -0.0000

Data Index: 124675 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1147809 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6731. Min Act: -0.0000

Data Index: 1182712 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6292. Min Act: -0.0000

Data Index: 924355 (C4 (Web Text))

Max Activating Token Index: 16