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

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

Neuron 3557 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0605. Min Act: -0.0001

Data Index: 124372 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1085509 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0540. Min Act: -0.0001

Data Index: 19608 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0576. Min Act: -0.0001

Data Index: 112054 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0562. Min Act: -0.0001

Data Index: 190121 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0594. Min Act: -0.0001

Data Index: 566720 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0508. Min Act: -0.0001

Data Index: 877267 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0501. Min Act: -0.0001

Data Index: 300936 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0538. Min Act: -0.0001

Data Index: 486495 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0519. Min Act: -0.0001

Data Index: 363643 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0537. Min Act: -0.0001

Data Index: 256011 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0455. Min Act: -0.0001

Data Index: 43781 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0522. Min Act: -0.0001

Data Index: 854259 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1226276 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0509. Min Act: -0.0001

Data Index: 340726 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0494. Min Act: -0.0001

Data Index: 676918 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0495. Min Act: -0.0001

Data Index: 922182 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1187374 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0473. Min Act: -0.0001

Data Index: 218389 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0478. Min Act: -0.0001

Data Index: 959249 (C4 (Web Text))

Max Activating Token Index: 112