Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6068 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.6254. Min Range: -5.6254

Max Act: 5.6254. Min Act: -0.0000

Data Index: 485041 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 5.6254. Min Range: -5.6254

Max Act: 5.3096. Min Act: -0.0000

Data Index: 505408 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 5.6254. Min Range: -5.6254

Max Act: 5.0068. Min Act: -0.0000

Data Index: 682301 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.6980. Min Act: -0.0000

Data Index: 873449 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.8354. Min Act: -0.0000

Data Index: 931887 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.8187. Min Act: -0.0000

Data Index: 877682 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.8194. Min Act: -0.0000

Data Index: 757574 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.5056. Min Act: -0.0000

Data Index: 807235 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.6093. Min Act: -0.0000

Data Index: 979815 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.5865. Min Act: -0.0000

Data Index: 922786 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.4824. Min Act: -0.0000

Data Index: 746667 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.4825. Min Act: -0.0000

Data Index: 581121 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.6664. Min Act: -0.0000

Data Index: 218862 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.4028. Min Act: -0.0000

Data Index: 139891 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.3654. Min Act: -0.0000

Data Index: 477402 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.5278. Min Act: -0.0000

Data Index: 1056784 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.1854. Min Act: -0.0000

Data Index: 802134 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.2006. Min Act: -0.0000

Data Index: 613223 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.1884. Min Act: -0.0000

Data Index: 719899 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 5.6254. Min Range: -5.6254

Max Act: 4.1077. Min Act: -0.0000

Data Index: 1303940 (C4 (Web Text))

Max Activating Token Index: 522