Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3867 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.8100. Min Act: -0.0002

Data Index: 1162454 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.7800. Min Act: -0.0002

Data Index: 388778 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.7665. Min Act: -0.0002

Data Index: 1014713 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.7657. Min Act: -0.0002

Data Index: 87599 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.7200. Min Act: -0.0002

Data Index: 914982 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.7287. Min Act: -0.0002

Data Index: 1321180 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.7499. Min Act: -0.0002

Data Index: 862393 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.7312. Min Act: -0.0002

Data Index: 1324383 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6961. Min Act: -0.0002

Data Index: 295856 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.7519. Min Act: -0.0002

Data Index: 1297530 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.7056. Min Act: -0.0002

Data Index: 496468 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6367. Min Act: -0.0002

Data Index: 571860 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.7182. Min Act: -0.0002

Data Index: 7437 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6867. Min Act: -0.0002

Data Index: 986016 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6608. Min Act: -0.0002

Data Index: 1358551 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6844. Min Act: -0.0002

Data Index: 116091 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6798. Min Act: -0.0002

Data Index: 100669 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6776. Min Act: -0.0002

Data Index: 640271 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6486. Min Act: -0.0002

Data Index: 316266 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.8100. Min Range: -0.8100

Max Act: 0.6412. Min Act: -0.0001

Data Index: 282825 (C4 (Web Text))

Max Activating Token Index: 966