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

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

Neuron 3810 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: 4.3761. Min Range: -4.3761

Max Act: 4.3761. Min Act: -0.0000

Data Index: 194090 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 4.3761. Min Range: -4.3761

Max Act: 3.7293. Min Act: -0.0000

Data Index: 29206 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 4.3761. Min Range: -4.3761

Max Act: 3.1556. Min Act: -0.0000

Data Index: 1132810 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 4.3761. Min Range: -4.3761

Max Act: 3.0483. Min Act: -0.0000

Data Index: 550272 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 4.3761. Min Range: -4.3761

Max Act: 3.1588. Min Act: 0.0000

Data Index: 1108876 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.7756. Min Act: -0.0000

Data Index: 1295336 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.9124. Min Act: -0.0000

Data Index: 1251531 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.7225. Min Act: -0.0000

Data Index: 903797 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.7032. Min Act: -0.0000

Data Index: 1067131 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 4.3761. Min Range: -4.3761

Max Act: 3.0080. Min Act: 0.0001

Data Index: 515527 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.7435. Min Act: -0.0000

Data Index: 525632 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.6622. Min Act: -0.0000

Data Index: 625259 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.6526. Min Act: 0.0000

Data Index: 760013 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.5792. Min Act: -0.0000

Data Index: 336965 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.4607. Min Act: -0.0000

Data Index: 737870 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.7096. Min Act: -0.0000

Data Index: 888627 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.5724. Min Act: -0.0000

Data Index: 749056 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.5654. Min Act: -0.0000

Data Index: 586305 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.5590. Min Act: -0.0000

Data Index: 225420 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 4.3761. Min Range: -4.3761

Max Act: 2.6329. Min Act: -0.0000

Data Index: 482490 (C4 (Web Text))

Max Activating Token Index: 91