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

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

Neuron 1169 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.8570. Min Act: -0.0000

Data Index: 830474 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.8380. Min Act: -0.0000

Data Index: 377550 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.7998. Min Act: -0.0000

Data Index: 1042069 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.6289. Min Act: -0.0000

Data Index: 141953 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.7120. Min Act: -0.0000

Data Index: 1240081 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.7874. Min Act: -0.0000

Data Index: 164866 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.6783. Min Act: -0.0000

Data Index: 1329638 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.5654. Min Act: -0.0000

Data Index: 460337 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.5355. Min Act: -0.0000

Data Index: 602909 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.6350. Min Act: -0.0000

Data Index: 605451 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.7020. Min Act: -0.0000

Data Index: 1040924 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.5652. Min Act: -0.0000

Data Index: 465161 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.5695. Min Act: -0.0000

Data Index: 1241487 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.5596. Min Act: -0.0000

Data Index: 958337 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.4842. Min Act: -0.0000

Data Index: 1192381 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.6554. Min Act: -0.0000

Data Index: 71477 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.5574. Min Act: -0.0000

Data Index: 522306 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.5578. Min Act: -0.0000

Data Index: 602876 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.5313. Min Act: -0.0000

Data Index: 1051341 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.8570. Min Range: -1.8570

Max Act: 1.6166. Min Act: -0.0000

Data Index: 920867 (C4 (Web Text))

Max Activating Token Index: 946