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

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

Neuron 3647 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1078871 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.8778. Min Act: -0.0000

Data Index: 87131 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7444. Min Act: -0.0001

Data Index: 137718 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7554. Min Act: -0.0001

Data Index: 1001154 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7754. Min Act: -0.0001

Data Index: 962991 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7615. Min Act: -0.0001

Data Index: 576175 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7317. Min Act: -0.0001

Data Index: 360577 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7046. Min Act: -0.0001

Data Index: 210643 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6646. Min Act: -0.0001

Data Index: 869999 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7255. Min Act: -0.0001

Data Index: 423285 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6795. Min Act: -0.0001

Data Index: 882205 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6889. Min Act: -0.0001

Data Index: 1225225 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.7332. Min Act: -0.0001

Data Index: 272280 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6605. Min Act: -0.0001

Data Index: 902957 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6593. Min Act: -0.0001

Data Index: 3686 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6153. Min Act: -0.0001

Data Index: 1070372 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6533. Min Act: -0.0001

Data Index: 302986 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6948. Min Act: -0.0001

Data Index: 1126508 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.6943. Min Act: -0.0001

Data Index: 49504 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.9110. Min Range: -0.9110

Max Act: 0.5852. Min Act: -0.0001

Data Index: 491597 (C4 (Web Text))

Max Activating Token Index: 133