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

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

Neuron 1703 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.6751. Min Act: -0.0000

Data Index: 269638 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.7523. Min Act: -0.0000

Data Index: 660049 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.7809. Min Act: -0.0000

Data Index: 218752 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.6745. Min Act: -0.0000

Data Index: 1054535 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.6360. Min Act: -0.0000

Data Index: 719469 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.6182. Min Act: -0.0000

Data Index: 840114 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.6026. Min Act: -0.0000

Data Index: 911714 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.6009. Min Act: -0.0000

Data Index: 421790 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4126. Min Act: -0.0000

Data Index: 828164 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4889. Min Act: -0.0000

Data Index: 1024509 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4027. Min Act: -0.0000

Data Index: 149882 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4331. Min Act: -0.0000

Data Index: 622768 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4175. Min Act: -0.0000

Data Index: 459423 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.3266. Min Act: -0.0000

Data Index: 216005 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4061. Min Act: -0.0000

Data Index: 1295590 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4067. Min Act: -0.0000

Data Index: 245708 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.3103. Min Act: -0.0000

Data Index: 146926 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.3938. Min Act: -0.0000

Data Index: 799422 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.3415. Min Act: -0.0000

Data Index: 771100 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 1.7809. Min Range: -1.7809

Max Act: 1.4649. Min Act: -0.0000

Data Index: 580791 (C4 (Web Text))

Max Activating Token Index: 335