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

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

Neuron 559 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: 1.0019. Min Range: -1.0019

Max Act: 0.9650. Min Act: -0.0002

Data Index: 1050339 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8998. Min Act: -0.0001

Data Index: 834403 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 1.0019. Min Range: -1.0019

Max Act: 1.0019. Min Act: -0.0002

Data Index: 1292823 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.9727. Min Act: -0.0002

Data Index: 388015 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.9065. Min Act: -0.0001

Data Index: 443863 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8991. Min Act: -0.0001

Data Index: 973526 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8625. Min Act: -0.0001

Data Index: 5210 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.9004. Min Act: -0.0002

Data Index: 784447 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8047. Min Act: -0.0001

Data Index: 1041858 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8661. Min Act: -0.0001

Data Index: 468470 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.9818. Min Act: -0.0001

Data Index: 596528 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8668. Min Act: -0.0001

Data Index: 594877 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7802. Min Act: -0.0002

Data Index: 843778 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7367. Min Act: -0.0002

Data Index: 172393 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8047. Min Act: -0.0002

Data Index: 839364 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7691. Min Act: -0.0002

Data Index: 1088854 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7673. Min Act: -0.0002

Data Index: 922151 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7566. Min Act: -0.0001

Data Index: 1117951 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8106. Min Act: -0.0002

Data Index: 662444 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7991. Min Act: -0.0001

Data Index: 1072308 (C4 (Web Text))

Max Activating Token Index: 643