Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 535 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2006. Min Range: -2.2006

Max Act: 2.1229. Min Act: -0.0000

Data Index: 969525 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 2.2006. Min Range: -2.2006

Max Act: 2.2006. Min Act: -0.0000

Data Index: 769446 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 2.2006. Min Range: -2.2006

Max Act: 2.0520. Min Act: -0.0000

Data Index: 1339997 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.8467. Min Act: -0.0000

Data Index: 187408 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.8418. Min Act: -0.0000

Data Index: 250886 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.7974. Min Act: -0.0000

Data Index: 1116054 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.7708. Min Act: -0.0000

Data Index: 505702 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.7436. Min Act: -0.0000

Data Index: 430163 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.6941. Min Act: -0.0000

Data Index: 777693 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.7395. Min Act: -0.0000

Data Index: 455728 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.5503. Min Act: -0.0000

Data Index: 627507 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.6147. Min Act: -0.0000

Data Index: 382671 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.5774. Min Act: -0.0000

Data Index: 649667 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.3874. Min Act: -0.0000

Data Index: 606389 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.3248. Min Act: -0.0000

Data Index: 12751 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.2296. Min Act: -0.0000

Data Index: 454040 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.2978. Min Act: -0.0000

Data Index: 949554 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.3822. Min Act: -0.0000

Data Index: 1000807 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.2326. Min Act: -0.0000

Data Index: 324515 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 2.2006. Min Range: -2.2006

Max Act: 1.2015. Min Act: -0.0000

Data Index: 1125062 (C4 (Web Text))

Max Activating Token Index: 35