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

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

Neuron 517 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: 0.4706. Min Range: -0.4706

Max Act: 0.4706. Min Act: -0.0000

Data Index: 42855 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4383. Min Act: -0.0000

Data Index: 564141 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4290. Min Act: 0.0000

Data Index: 868796 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4432. Min Act: 0.0000

Data Index: 1024351 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4219. Min Act: -0.0000

Data Index: 549075 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4208. Min Act: 0.0000

Data Index: 382580 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4207. Min Act: 0.0000

Data Index: 1134175 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1244242 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1024308 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3982. Min Act: -0.0000

Data Index: 893098 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3895. Min Act: 0.0000

Data Index: 1178494 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1200726 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1295320 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3952. Min Act: -0.0000

Data Index: 678586 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1298124 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3792. Min Act: -0.0000

Data Index: 766301 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1155727 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3724. Min Act: 0.0000

Data Index: 1153255 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3664. Min Act: -0.0000

Data Index: 629755 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3679. Min Act: 0.0000

Data Index: 973100 (C4 (Web Text))

Max Activating Token Index: 817