Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2214 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5984. Min Act: -0.0001

Data Index: 777792 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5392. Min Act: -0.0001

Data Index: 1581269 (Python Code)

Max Activating Token Index: 505

Text #2

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5702. Min Act: -0.0001

Data Index: 282552 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5678. Min Act: -0.0001

Data Index: 817358 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5859. Min Act: -0.0001

Data Index: 846489 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5638. Min Act: -0.0001

Data Index: 1588441 (Python Code)

Max Activating Token Index: 477

Text #6

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5670. Min Act: -0.0001

Data Index: 1547704 (Python Code)

Max Activating Token Index: 623

Text #7

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5257. Min Act: -0.0001

Data Index: 64045 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5417. Min Act: -0.0001

Data Index: 751875 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5329. Min Act: -0.0001

Data Index: 1246196 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5118. Min Act: -0.0001

Data Index: 153805 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5268. Min Act: -0.0001

Data Index: 279942 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5255. Min Act: -0.0001

Data Index: 1386686 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5238. Min Act: -0.0001

Data Index: 1316961 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5202. Min Act: -0.0001

Data Index: 833757 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5216. Min Act: -0.0001

Data Index: 787127 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5042. Min Act: -0.0001

Data Index: 1501537 (Python Code)

Max Activating Token Index: 245

Text #17

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5251. Min Act: -0.0001

Data Index: 609660 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5046. Min Act: -0.0001

Data Index: 221737 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5144. Min Act: -0.0001

Data Index: 954957 (C4 (Web Text))

Max Activating Token Index: 338