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

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

Neuron 2309 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0003

Data Index: 359549 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0534. Min Act: -0.0003

Data Index: 853209 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0617. Min Act: -0.0004

Data Index: 776360 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1203300 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0657. Min Act: -0.0003

Data Index: 773476 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0534. Min Act: -0.0003

Data Index: 603406 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1057077 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0590. Min Act: -0.0003

Data Index: 328407 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0418. Min Act: -0.0003

Data Index: 1121390 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0506. Min Act: -0.0003

Data Index: 1326493 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1115193 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0512. Min Act: -0.0003

Data Index: 480843 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0601. Min Act: -0.0003

Data Index: 919554 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0473. Min Act: -0.0003

Data Index: 580519 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0550. Min Act: -0.0004

Data Index: 83846 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0490. Min Act: -0.0003

Data Index: 573058 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0505. Min Act: -0.0003

Data Index: 1301149 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0505. Min Act: -0.0004

Data Index: 223807 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0505. Min Act: -0.0003

Data Index: 1190945 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0505. Min Act: -0.0003

Data Index: 386933 (C4 (Web Text))

Max Activating Token Index: 3