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

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

Neuron 3529 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0847. Min Act: -0.0001

Data Index: 1298374 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0665. Min Act: -0.0001

Data Index: 931184 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1338365 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1120882 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0751. Min Act: -0.0001

Data Index: 708800 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0685. Min Act: -0.0001

Data Index: 932849 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1638786 (Python Code)

Max Activating Token Index: 324

Text #7

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0666. Min Act: -0.0001

Data Index: 911273 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0650. Min Act: -0.0001

Data Index: 400540 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0644. Min Act: -0.0001

Data Index: 203971 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1311844 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1392534 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0655. Min Act: -0.0001

Data Index: 147013 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0636. Min Act: -0.0001

Data Index: 346989 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0628. Min Act: -0.0001

Data Index: 402966 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0639. Min Act: -0.0001

Data Index: 298009 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0630. Min Act: -0.0001

Data Index: 624251 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0617. Min Act: -0.0001

Data Index: 493140 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0617. Min Act: -0.0001

Data Index: 905320 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1320223 (C4 (Web Text))

Max Activating Token Index: 563