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

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

Neuron 2685 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1294. Min Act: -0.0001

Data Index: 666619 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1302. Min Act: -0.0001

Data Index: 946248 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1136. Min Act: -0.0001

Data Index: 704251 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0991. Min Act: -0.0001

Data Index: 281486 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1019. Min Act: -0.0001

Data Index: 84605 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1091914 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1352082 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0870. Min Act: -0.0001

Data Index: 914522 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0859. Min Act: -0.0001

Data Index: 848653 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0934. Min Act: -0.0001

Data Index: 87804 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0880. Min Act: -0.0001

Data Index: 569214 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0922. Min Act: -0.0001

Data Index: 721560 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0881. Min Act: -0.0001

Data Index: 455621 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0850. Min Act: -0.0001

Data Index: 659909 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1156089 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0839. Min Act: -0.0001

Data Index: 4137 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1332865 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0829. Min Act: -0.0001

Data Index: 427502 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0793. Min Act: -0.0001

Data Index: 410655 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0844. Min Act: -0.0001

Data Index: 601054 (C4 (Web Text))

Max Activating Token Index: 494