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

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

Neuron 1093 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.8982. Min Act: -0.0000

Data Index: 194254 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.8444. Min Act: -0.0000

Data Index: 349238 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.7205. Min Act: 0.0000

Data Index: 1113364 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.6805. Min Act: -0.0000

Data Index: 550273 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.6639. Min Act: -0.0000

Data Index: 754162 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5341. Min Act: -0.0000

Data Index: 916284 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5791. Min Act: -0.0000

Data Index: 22741 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5382. Min Act: -0.0000

Data Index: 749180 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5443. Min Act: -0.0000

Data Index: 1198153 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5150. Min Act: -0.0000

Data Index: 821234 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5009. Min Act: 0.0000

Data Index: 11658 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5680. Min Act: -0.0000

Data Index: 205212 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.4832. Min Act: -0.0000

Data Index: 545808 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.4516. Min Act: -0.0000

Data Index: 24665 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.4190. Min Act: -0.0000

Data Index: 1039157 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1243060 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1275065 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.3119. Min Act: -0.0000

Data Index: 1228152 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.3685. Min Act: -0.0000

Data Index: 1188330 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.3651. Min Act: -0.0000

Data Index: 687927 (C4 (Web Text))

Max Activating Token Index: 271