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

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

Neuron 4231 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7853. Min Act: -0.0001

Data Index: 390115 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7158. Min Act: -0.0001

Data Index: 368587 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7117. Min Act: -0.0001

Data Index: 261172 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6426. Min Act: -0.0001

Data Index: 687454 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6506. Min Act: -0.0001

Data Index: 427756 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6145. Min Act: -0.0001

Data Index: 1011902 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6263. Min Act: -0.0001

Data Index: 1090926 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6225. Min Act: -0.0001

Data Index: 865019 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6042. Min Act: -0.0001

Data Index: 233681 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6299. Min Act: -0.0001

Data Index: 477896 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6291. Min Act: -0.0001

Data Index: 650054 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6371. Min Act: -0.0001

Data Index: 813536 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6161. Min Act: -0.0001

Data Index: 373236 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5378. Min Act: -0.0001

Data Index: 127496 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5913. Min Act: -0.0001

Data Index: 558381 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5968. Min Act: -0.0001

Data Index: 473877 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6102. Min Act: -0.0001

Data Index: 1029060 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6395. Min Act: -0.0001

Data Index: 968623 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6132. Min Act: -0.0001

Data Index: 1102165 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6078. Min Act: -0.0001

Data Index: 390465 (C4 (Web Text))

Max Activating Token Index: 782