Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 782 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0914. Min Act: -0.0003

Data Index: 1347862 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0844. Min Act: -0.0003

Data Index: 1093661 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0762. Min Act: -0.0003

Data Index: 223471 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0802. Min Act: -0.0003

Data Index: 290775 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0760. Min Act: -0.0003

Data Index: 499185 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0694. Min Act: -0.0003

Data Index: 998950 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0713. Min Act: -0.0003

Data Index: 840985 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1249178 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0709. Min Act: -0.0003

Data Index: 255513 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0702. Min Act: -0.0003

Data Index: 517832 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0698. Min Act: -0.0003

Data Index: 701651 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0669. Min Act: -0.0003

Data Index: 180586 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0690. Min Act: -0.0003

Data Index: 65743 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0715. Min Act: -0.0003

Data Index: 313430 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1348242 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0631. Min Act: -0.0003

Data Index: 596368 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0704. Min Act: -0.0003

Data Index: 674039 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1071199 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0647. Min Act: -0.0003

Data Index: 918749 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0671. Min Act: -0.0003

Data Index: 617006 (C4 (Web Text))

Max Activating Token Index: 466