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

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

Neuron 1220 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0818. Min Act: -0.0000

Data Index: 428642 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1054546 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0617. Min Act: -0.0000

Data Index: 651043 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0624. Min Act: -0.0000

Data Index: 340731 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0639. Min Act: -0.0000

Data Index: 911049 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0598. Min Act: -0.0000

Data Index: 540017 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0726. Min Act: -0.0000

Data Index: 597814 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0671. Min Act: -0.0000

Data Index: 738797 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0608. Min Act: -0.0000

Data Index: 621137 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1344052 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0564. Min Act: -0.0000

Data Index: 700268 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0584. Min Act: -0.0000

Data Index: 12236 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1176084 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0632. Min Act: -0.0000

Data Index: 294741 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0618. Min Act: -0.0000

Data Index: 51383 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0617. Min Act: -0.0000

Data Index: 1232267 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0530. Min Act: -0.0000

Data Index: 402185 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0570. Min Act: -0.0000

Data Index: 587928 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0598. Min Act: -0.0000

Data Index: 507405 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0557. Min Act: -0.0000

Data Index: 429683 (C4 (Web Text))

Max Activating Token Index: 86