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

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

Neuron 3608 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: 0.7798. Min Range: -0.7798

Max Act: 0.7798. Min Act: -0.0001

Data Index: 964095 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.7481. Min Act: -0.0001

Data Index: 1046716 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.6749. Min Act: -0.0002

Data Index: 1142289 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.6635. Min Act: -0.0002

Data Index: 346516 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.6181. Min Act: -0.0002

Data Index: 83280 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.6734. Min Act: -0.0001

Data Index: 122398 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.6154. Min Act: -0.0001

Data Index: 1056087 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.6659. Min Act: -0.0001

Data Index: 117070 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.6086. Min Act: -0.0002

Data Index: 232910 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.5951. Min Act: -0.0002

Data Index: 437418 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.5321. Min Act: -0.0002

Data Index: 1060492 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.5811. Min Act: -0.0002

Data Index: 285451 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.5888. Min Act: -0.0002

Data Index: 466648 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.5677. Min Act: -0.0002

Data Index: 1222386 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.5844. Min Act: -0.0001

Data Index: 980487 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.5910. Min Act: -0.0001

Data Index: 903968 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.5818. Min Act: -0.0001

Data Index: 651542 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.5389. Min Act: -0.0002

Data Index: 53205 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.5631. Min Act: -0.0002

Data Index: 330053 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.7798. Min Range: -0.7798

Max Act: 0.5548. Min Act: -0.0001

Data Index: 885612 (C4 (Web Text))

Max Activating Token Index: 431