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

Dataset: The Pile

Neuron 3669 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: 0.0000

Data Index: 81798 (The Pile)

Max Activating Token Index: 14

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1027677 (The Pile)

Max Activating Token Index: 4

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0399. Min Act: 0.0000

Data Index: 7592 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0403. Min Act: -0.0000

Data Index: 1859487 (The Pile)

Max Activating Token Index: 4

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0385. Min Act: 0.0000

Data Index: 1217359 (The Pile)

Max Activating Token Index: 3

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0383. Min Act: -0.0000

Data Index: 283404 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0000

Data Index: 26365 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1086312 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0000

Data Index: 815538 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0000

Data Index: 4510 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0000

Data Index: 406698 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1223196 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: 0.0000

Data Index: 705384 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0000

Data Index: 704330 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0000

Data Index: 988596 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0000

Data Index: 407742 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0000

Data Index: 687555 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1041370 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1124432 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1518377 (The Pile)

Max Activating Token Index: 1