Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2008 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4628. Min Act: -0.0003

Data Index: 649509 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4321. Min Act: -0.0003

Data Index: 1064239 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4757. Min Act: -0.0003

Data Index: 104456 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4285. Min Act: -0.0003

Data Index: 1340151 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4400. Min Act: -0.0003

Data Index: 303977 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4034. Min Act: -0.0003

Data Index: 364980 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4147. Min Act: -0.0003

Data Index: 536137 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4188. Min Act: -0.0003

Data Index: 712898 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3850. Min Act: -0.0003

Data Index: 464401 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3974. Min Act: -0.0003

Data Index: 772826 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4064. Min Act: -0.0003

Data Index: 116958 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4034. Min Act: -0.0003

Data Index: 65447 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4011. Min Act: -0.0003

Data Index: 291234 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4292. Min Act: -0.0003

Data Index: 442157 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3896. Min Act: -0.0003

Data Index: 1078524 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3929. Min Act: -0.0003

Data Index: 1035612 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3929. Min Act: -0.0003

Data Index: 1014697 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3918. Min Act: -0.0003

Data Index: 91169 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3797. Min Act: -0.0003

Data Index: 376211 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3906. Min Act: -0.0003

Data Index: 1314036 (C4 (Web Text))

Max Activating Token Index: 450