Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 353 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.9075. Min Act: 0.0000

Data Index: 69525 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.8229. Min Act: -0.0000

Data Index: 526217 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.6715. Min Act: 0.0000

Data Index: 311277 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.7189. Min Act: -0.0000

Data Index: 944074 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.6197. Min Act: -0.0000

Data Index: 659596 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.6059. Min Act: -0.0000

Data Index: 559043 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.5178. Min Act: -0.0000

Data Index: 906412 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.4998. Min Act: -0.0000

Data Index: 1138269 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.4974. Min Act: -0.0000

Data Index: 760400 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.4931. Min Act: -0.0000

Data Index: 542245 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.4404. Min Act: -0.0000

Data Index: 1048985 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.4424. Min Act: -0.0000

Data Index: 480583 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.4801. Min Act: -0.0000

Data Index: 213899 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.4657. Min Act: -0.0000

Data Index: 68242 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.3867. Min Act: -0.0000

Data Index: 728840 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.4221. Min Act: -0.0000

Data Index: 526472 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.4256. Min Act: -0.0000

Data Index: 524539 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.4218. Min Act: 0.0002

Data Index: 1065277 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.3831. Min Act: 0.0000

Data Index: 393228 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 1.9075. Min Range: -1.9075

Max Act: 1.3723. Min Act: 0.0000

Data Index: 981271 (C4 (Web Text))

Max Activating Token Index: 1013