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

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

Neuron 1971 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.8381. Min Act: -0.0000

Data Index: 134672 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6595. Min Act: -0.0000

Data Index: 334158 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.5291. Min Act: -0.0000

Data Index: 820023 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.4761. Min Act: -0.0000

Data Index: 903597 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.5232. Min Act: -0.0000

Data Index: 321838 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.4675. Min Act: -0.0000

Data Index: 910008 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.4605. Min Act: -0.0000

Data Index: 515736 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.5018. Min Act: -0.0000

Data Index: 612540 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.4654. Min Act: -0.0000

Data Index: 904057 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.4804. Min Act: -0.0000

Data Index: 769629 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.4357. Min Act: -0.0000

Data Index: 515975 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.4202. Min Act: -0.0000

Data Index: 545911 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1193893 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.4075. Min Act: -0.0000

Data Index: 177017 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.4457. Min Act: -0.0000

Data Index: 932597 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.4084. Min Act: -0.0000

Data Index: 220349 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.3873. Min Act: -0.0000

Data Index: 16642 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1243902 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.4120. Min Act: -0.0000

Data Index: 474672 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.3971. Min Act: -0.0000

Data Index: 60657 (C4 (Web Text))

Max Activating Token Index: 920