Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1851 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8505. Min Act: -0.0001

Data Index: 463579 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8391. Min Act: -0.0001

Data Index: 1279061 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7838. Min Act: -0.0001

Data Index: 368438 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7326. Min Act: -0.0001

Data Index: 561969 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7124. Min Act: -0.0001

Data Index: 1233942 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6819. Min Act: -0.0001

Data Index: 567305 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7019. Min Act: -0.0001

Data Index: 722514 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6655. Min Act: -0.0001

Data Index: 1291369 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6595. Min Act: -0.0001

Data Index: 888643 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6855. Min Act: -0.0001

Data Index: 1063836 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7026. Min Act: -0.0001

Data Index: 895235 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7189. Min Act: -0.0001

Data Index: 83908 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7031. Min Act: -0.0001

Data Index: 1239138 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6659. Min Act: -0.0001

Data Index: 36814 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6509. Min Act: -0.0001

Data Index: 126226 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6835. Min Act: -0.0001

Data Index: 1261676 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6840. Min Act: -0.0001

Data Index: 204620 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6992. Min Act: -0.0001

Data Index: 201280 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6876. Min Act: -0.0001

Data Index: 541762 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6481. Min Act: -0.0001

Data Index: 1119586 (C4 (Web Text))

Max Activating Token Index: 49