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

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

Neuron 4937 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.9022. Min Act: -0.0000

Data Index: 262018 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.6660. Min Act: -0.0000

Data Index: 997845 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.4829. Min Act: -0.0000

Data Index: 818671 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.7429. Min Act: -0.0000

Data Index: 71573 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.7428. Min Act: -0.0000

Data Index: 1325800 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.6376. Min Act: -0.0000

Data Index: 1208311 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.7235. Min Act: -0.0000

Data Index: 426637 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.4577. Min Act: -0.0000

Data Index: 1233859 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.5647. Min Act: -0.0000

Data Index: 197939 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.6534. Min Act: -0.0000

Data Index: 944083 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.7943. Min Act: -0.0000

Data Index: 24050 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.3650. Min Act: -0.0000

Data Index: 125215 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.5226. Min Act: -0.0000

Data Index: 457563 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1640108 (Python Code)

Max Activating Token Index: 735

Text #14

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.6085. Min Act: -0.0000

Data Index: 12039 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.5422. Min Act: -0.0001

Data Index: 1616131 (Python Code)

Max Activating Token Index: 118

Text #16

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.5657. Min Act: -0.0000

Data Index: 1434693 (Python Code)

Max Activating Token Index: 998

Text #17

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.5290. Min Act: -0.0000

Data Index: 1557774 (Python Code)

Max Activating Token Index: 178

Text #18

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.5787. Min Act: -0.0000

Data Index: 466346 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.5020. Min Act: -0.0000

Data Index: 648177 (C4 (Web Text))

Max Activating Token Index: 422