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

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

Neuron 1791 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.8238. Min Act: -0.0000

Data Index: 586809 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.8191. Min Act: -0.0000

Data Index: 857363 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.5560. Min Act: 0.0000

Data Index: 244286 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.5247. Min Act: -0.0000

Data Index: 876530 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4914. Min Act: -0.0000

Data Index: 616060 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.5119. Min Act: -0.0000

Data Index: 187452 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4620. Min Act: 0.0000

Data Index: 13091 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4918. Min Act: -0.0000

Data Index: 234815 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4748. Min Act: -0.0000

Data Index: 369505 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1227586 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4365. Min Act: -0.0000

Data Index: 410753 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4492. Min Act: -0.0000

Data Index: 262594 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4541. Min Act: -0.0000

Data Index: 331730 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4436. Min Act: -0.0000

Data Index: 310023 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4213. Min Act: -0.0000

Data Index: 127838 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4742. Min Act: -0.0000

Data Index: 266082 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1109201 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4324. Min Act: 0.0000

Data Index: 901297 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4291. Min Act: -0.0000

Data Index: 741140 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.8238. Min Range: -0.8238

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1001855 (C4 (Web Text))

Max Activating Token Index: 396