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

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

Neuron 3253 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: 3.2217. Min Range: -3.2217

Max Act: 2.9998. Min Act: -0.0000

Data Index: 59402 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 3.2217. Min Range: -3.2217

Max Act: 3.2217. Min Act: -0.0000

Data Index: 1337973 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.8943. Min Act: -0.0000

Data Index: 1343954 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 3.2217. Min Range: -3.2217

Max Act: 3.0061. Min Act: -0.0000

Data Index: 552056 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.8312. Min Act: -0.0000

Data Index: 1291354 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.4798. Min Act: -0.0000

Data Index: 117497 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.8601. Min Act: -0.0000

Data Index: 1244464 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.6971. Min Act: -0.0000

Data Index: 980293 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.5058. Min Act: -0.0000

Data Index: 1561298 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.6094. Min Act: -0.0000

Data Index: 685914 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.7218. Min Act: -0.0000

Data Index: 1019358 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.5995. Min Act: -0.0000

Data Index: 689966 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.6139. Min Act: -0.0000

Data Index: 1220765 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.4256. Min Act: -0.0000

Data Index: 995811 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.5427. Min Act: -0.0000

Data Index: 1349979 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.5304. Min Act: -0.0000

Data Index: 486754 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.5029. Min Act: -0.0000

Data Index: 791657 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.5198. Min Act: -0.0000

Data Index: 450712 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.5159. Min Act: -0.0000

Data Index: 1124759 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.4980. Min Act: -0.0000

Data Index: 1249723 (C4 (Web Text))

Max Activating Token Index: 743