Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4278 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3516. Min Act: -0.0000

Data Index: 744404 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3506. Min Act: -0.0000

Data Index: 723465 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3370. Min Act: -0.0000

Data Index: 228111 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3283. Min Act: -0.0000

Data Index: 4748 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1566543 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3216. Min Act: -0.0000

Data Index: 552430 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1635319 (Python Code)

Max Activating Token Index: 342

Text #7

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2820. Min Act: -0.0000

Data Index: 877812 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2915. Min Act: -0.0000

Data Index: 680191 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1466571 (Python Code)

Max Activating Token Index: 544

Text #10

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3007. Min Act: -0.0000

Data Index: 779325 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1488642 (Python Code)

Max Activating Token Index: 995

Text #12

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1437979 (Python Code)

Max Activating Token Index: 660

Text #13

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2780. Min Act: -0.0000

Data Index: 582447 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1450246 (Python Code)

Max Activating Token Index: 180

Text #15

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1198171 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1097941 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1431917 (Python Code)

Max Activating Token Index: 781

Text #18

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2646. Min Act: -0.0000

Data Index: 720473 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1568356 (Python Code)

Max Activating Token Index: 670