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

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

Neuron 2425 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.8013. Min Act: -0.0001

Data Index: 350358 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.5433. Min Act: -0.0001

Data Index: 153617 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.9542. Min Act: -0.0001

Data Index: 787757 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.0104. Min Act: -0.0001

Data Index: 835596 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.9693. Min Act: -0.0001

Data Index: 992374 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.8537. Min Act: -0.0001

Data Index: 964422 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.7175. Min Act: -0.0001

Data Index: 606561 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.8218. Min Act: -0.0001

Data Index: 254488 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.8281. Min Act: -0.0001

Data Index: 377686 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.6787. Min Act: -0.0001

Data Index: 849551 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.4744. Min Act: -0.0001

Data Index: 251348 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.6625. Min Act: -0.0001

Data Index: 817196 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.7619. Min Act: -0.0001

Data Index: 896493 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.8201. Min Act: -0.0001

Data Index: 816828 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.5168. Min Act: -0.0001

Data Index: 983119 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.4875. Min Act: -0.0001

Data Index: 89831 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.4679. Min Act: -0.0001

Data Index: 839819 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.4606. Min Act: -0.0001

Data Index: 1176692 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.5852. Min Act: -0.0001

Data Index: 1017627 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 3.8013. Min Range: -3.8013

Max Act: 2.5858. Min Act: -0.0001

Data Index: 636764 (C4 (Web Text))

Max Activating Token Index: 9