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

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

Neuron 3939 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8815. Min Act: -0.0001

Data Index: 683127 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8816. Min Act: -0.0001

Data Index: 1145744 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8746. Min Act: -0.0001

Data Index: 172773 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8232. Min Act: -0.0001

Data Index: 1229068 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8057. Min Act: -0.0001

Data Index: 515817 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8062. Min Act: -0.0001

Data Index: 874392 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7662. Min Act: -0.0001

Data Index: 700622 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7634. Min Act: -0.0001

Data Index: 130604 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7600. Min Act: -0.0001

Data Index: 1314585 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8131. Min Act: -0.0001

Data Index: 1056326 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7394. Min Act: -0.0001

Data Index: 1440131 (Python Code)

Max Activating Token Index: 527

Text #11

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7153. Min Act: -0.0001

Data Index: 603726 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7293. Min Act: -0.0001

Data Index: 954172 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6851. Min Act: -0.0001

Data Index: 623789 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7735. Min Act: -0.0001

Data Index: 324362 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6694. Min Act: -0.0001

Data Index: 604876 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7097. Min Act: -0.0001

Data Index: 868191 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6675. Min Act: -0.0001

Data Index: 875343 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7126. Min Act: -0.0001

Data Index: 1334714 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6626. Min Act: -0.0001

Data Index: 703117 (C4 (Web Text))

Max Activating Token Index: 270