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

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

Neuron 244 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: 0.2769. Min Range: -0.2769

Max Act: 0.2769. Min Act: -0.0000

Data Index: 715374 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2195. Min Act: -0.0001

Data Index: 795595 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1975. Min Act: -0.0000

Data Index: 689648 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2066. Min Act: -0.0001

Data Index: 1229089 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2159. Min Act: -0.0001

Data Index: 461833 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1893. Min Act: -0.0000

Data Index: 938868 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2003. Min Act: -0.0001

Data Index: 1049892 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1925. Min Act: -0.0001

Data Index: 978150 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1829. Min Act: -0.0001

Data Index: 147564 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1912. Min Act: -0.0001

Data Index: 227809 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1845. Min Act: -0.0001

Data Index: 221153 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1909. Min Act: -0.0001

Data Index: 483061 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1813. Min Act: -0.0001

Data Index: 432619 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1612. Min Act: -0.0001

Data Index: 290564 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1724. Min Act: -0.0001

Data Index: 708407 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1594. Min Act: -0.0000

Data Index: 577794 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1703. Min Act: -0.0001

Data Index: 439742 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1788. Min Act: -0.0001

Data Index: 157518 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1212749 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1649. Min Act: -0.0001

Data Index: 870405 (C4 (Web Text))

Max Activating Token Index: 477