Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 834 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3659. Min Act: -0.0001

Data Index: 396086 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3341. Min Act: -0.0001

Data Index: 1204006 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3375. Min Act: -0.0001

Data Index: 774654 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3404. Min Act: -0.0001

Data Index: 660911 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3179. Min Act: -0.0001

Data Index: 481129 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3002. Min Act: -0.0001

Data Index: 799895 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3092. Min Act: -0.0001

Data Index: 275543 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3088. Min Act: -0.0001

Data Index: 605496 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2896. Min Act: -0.0001

Data Index: 1028502 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2742. Min Act: -0.0001

Data Index: 181187 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2904. Min Act: -0.0001

Data Index: 948221 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2999. Min Act: -0.0001

Data Index: 710351 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2846. Min Act: -0.0001

Data Index: 438938 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2853. Min Act: -0.0001

Data Index: 992163 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2950. Min Act: -0.0001

Data Index: 306872 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2841. Min Act: -0.0001

Data Index: 777918 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2825. Min Act: -0.0001

Data Index: 319252 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2732. Min Act: -0.0001

Data Index: 100691 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2824. Min Act: -0.0001

Data Index: 977309 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2645. Min Act: -0.0001

Data Index: 1005039 (C4 (Web Text))

Max Activating Token Index: 776