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

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

Neuron 1546 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: 0.5686. Min Range: -0.5686

Max Act: 0.5609. Min Act: -0.0000

Data Index: 299675 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5686. Min Act: -0.0000

Data Index: 859434 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1006639 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5006. Min Act: -0.0000

Data Index: 569281 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5356. Min Act: 0.0000

Data Index: 627860 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4927. Min Act: -0.0000

Data Index: 741308 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4852. Min Act: -0.0000

Data Index: 133166 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1283484 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1042918 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4464. Min Act: -0.0000

Data Index: 184668 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4233. Min Act: -0.0000

Data Index: 552816 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1202235 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.3650. Min Act: -0.0000

Data Index: 463108 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4173. Min Act: -0.0000

Data Index: 515032 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4158. Min Act: 0.0000

Data Index: 209572 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4031. Min Act: -0.0000

Data Index: 580209 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4165. Min Act: -0.0000

Data Index: 122336 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1339512 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.3828. Min Act: -0.0000

Data Index: 961165 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4068. Min Act: -0.0000

Data Index: 335955 (C4 (Web Text))

Max Activating Token Index: 854