Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3061 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.9837. Min Act: -0.0000

Data Index: 709493 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1195091 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.8931. Min Act: -0.0000

Data Index: 583683 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.9156. Min Act: -0.0000

Data Index: 771815 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7030. Min Act: -0.0000

Data Index: 300977 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7652. Min Act: -0.0000

Data Index: 746260 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7128. Min Act: -0.0000

Data Index: 476271 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.6315. Min Act: -0.0000

Data Index: 386763 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.6549. Min Act: -0.0000

Data Index: 672551 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.6171. Min Act: -0.0000

Data Index: 387944 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.6112. Min Act: -0.0000

Data Index: 495013 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.6104. Min Act: -0.0000

Data Index: 722471 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1194978 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.5934. Min Act: -0.0000

Data Index: 663469 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.5864. Min Act: -0.0000

Data Index: 66612 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.5490. Min Act: -0.0000

Data Index: 373468 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.4945. Min Act: -0.0000

Data Index: 723057 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.6045. Min Act: -0.0000

Data Index: 956456 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.6190. Min Act: -0.0000

Data Index: 866515 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1165596 (C4 (Web Text))

Max Activating Token Index: 151