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

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

Neuron 4502 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.7545. Min Act: -0.0000

Data Index: 441529 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1349483 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.3266. Min Act: -0.0000

Data Index: 226080 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.3281. Min Act: -0.0000

Data Index: 987442 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.3182. Min Act: -0.0000

Data Index: 24675 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.3126. Min Act: -0.0000

Data Index: 12397 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.2759. Min Act: -0.0000

Data Index: 333224 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.2677. Min Act: -0.0000

Data Index: 593105 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.3070. Min Act: -0.0000

Data Index: 107095 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1247920 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.2684. Min Act: -0.0000

Data Index: 94766 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1278578 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1180450 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.2517. Min Act: -0.0000

Data Index: 834434 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.2119. Min Act: -0.0000

Data Index: 341104 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.2265. Min Act: -0.0000

Data Index: 972291 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.2351. Min Act: -0.0000

Data Index: 126500 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.2423. Min Act: -0.0000

Data Index: 692583 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.2607. Min Act: -0.0000

Data Index: 400474 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1003778 (C4 (Web Text))

Max Activating Token Index: 610