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

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

Neuron 3020 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.6006. Min Act: -0.0000

Data Index: 432012 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5181. Min Act: -0.0000

Data Index: 186565 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1035596 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1293957 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5280. Min Act: -0.0000

Data Index: 443877 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5288. Min Act: -0.0000

Data Index: 441921 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1014801 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5169. Min Act: -0.0000

Data Index: 265035 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5308. Min Act: -0.0000

Data Index: 727355 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4960. Min Act: -0.0000

Data Index: 246028 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1243248 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1218880 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4828. Min Act: -0.0000

Data Index: 64050 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1035656 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1346339 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4701. Min Act: -0.0000

Data Index: 520876 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5037. Min Act: -0.0000

Data Index: 915022 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5126. Min Act: -0.0000

Data Index: 862051 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4690. Min Act: -0.0000

Data Index: 168804 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4612. Min Act: -0.0000

Data Index: 962352 (C4 (Web Text))

Max Activating Token Index: 177