Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 172 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0799. Min Act: -0.0002

Data Index: 552580 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1034266 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0716. Min Act: -0.0001

Data Index: 842028 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1076044 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0692. Min Act: -0.0001

Data Index: 553408 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0654. Min Act: 0.0000

Data Index: 1279210 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0717. Min Act: -0.0001

Data Index: 330253 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0678. Min Act: -0.0001

Data Index: 337036 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0672. Min Act: -0.0001

Data Index: 321845 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0661. Min Act: -0.0001

Data Index: 188115 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1091064 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0672. Min Act: -0.0001

Data Index: 232908 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0625. Min Act: -0.0002

Data Index: 339186 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1100662 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0630. Min Act: -0.0001

Data Index: 53046 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0677. Min Act: -0.0001

Data Index: 197659 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0638. Min Act: -0.0001

Data Index: 824971 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0640. Min Act: 0.0001

Data Index: 1252071 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0640. Min Act: -0.0001

Data Index: 351164 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0617. Min Act: -0.0001

Data Index: 739595 (C4 (Web Text))

Max Activating Token Index: 444