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

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

Neuron 1979 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.9013. Min Act: -0.0000

Data Index: 624647 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.7994. Min Act: -0.0000

Data Index: 1327351 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.7501. Min Act: -0.0000

Data Index: 784676 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.6804. Min Act: -0.0000

Data Index: 490544 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.4811. Min Act: -0.0000

Data Index: 243239 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.5637. Min Act: -0.0000

Data Index: 706951 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.5201. Min Act: -0.0000

Data Index: 1314025 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.5288. Min Act: -0.0000

Data Index: 58322 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.4553. Min Act: -0.0000

Data Index: 919026 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.4413. Min Act: -0.0000

Data Index: 393950 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.4907. Min Act: -0.0000

Data Index: 1064005 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.3699. Min Act: -0.0000

Data Index: 1021568 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.3616. Min Act: -0.0000

Data Index: 745576 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.3047. Min Act: -0.0000

Data Index: 14315 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.1812. Min Act: -0.0000

Data Index: 202701 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.1755. Min Act: -0.0000

Data Index: 611752 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.2244. Min Act: -0.0000

Data Index: 251588 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.2228. Min Act: -0.0000

Data Index: 182259 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.2219. Min Act: -0.0000

Data Index: 476078 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 1.9013. Min Range: -1.9013

Max Act: 1.2216. Min Act: -0.0000

Data Index: 811166 (C4 (Web Text))

Max Activating Token Index: 304