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

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

Neuron 1199 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2379. Min Range: -4.2379

Max Act: 4.2379. Min Act: -0.0000

Data Index: 1065116 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 4.2379. Min Range: -4.2379

Max Act: 4.0932. Min Act: -0.0000

Data Index: 434441 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 4.2379. Min Range: -4.2379

Max Act: 4.1362. Min Act: -0.0000

Data Index: 260468 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.7744. Min Act: -0.0000

Data Index: 79148 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.6183. Min Act: -0.0000

Data Index: 17891 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.9032. Min Act: -0.0000

Data Index: 819709 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.6373. Min Act: -0.0000

Data Index: 543766 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.6097. Min Act: -0.0000

Data Index: 1187192 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.5980. Min Act: -0.0000

Data Index: 488068 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.7353. Min Act: -0.0000

Data Index: 156048 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.5231. Min Act: -0.0000

Data Index: 212380 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.4993. Min Act: -0.0000

Data Index: 1086787 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.4996. Min Act: -0.0000

Data Index: 713241 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.4681. Min Act: -0.0000

Data Index: 40514 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.4623. Min Act: -0.0000

Data Index: 806506 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.4093. Min Act: -0.0000

Data Index: 90064 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.5675. Min Act: -0.0000

Data Index: 88754 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.4023. Min Act: -0.0000

Data Index: 243486 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.3922. Min Act: -0.0000

Data Index: 1043108 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 4.2379. Min Range: -4.2379

Max Act: 3.3778. Min Act: -0.0000

Data Index: 535166 (C4 (Web Text))

Max Activating Token Index: 171