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

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

Neuron 646 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1073747 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1304385 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.6305. Min Act: -0.0000

Data Index: 197979 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1582050 (Python Code)

Max Activating Token Index: 613

Text #4

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.6016. Min Act: -0.0000

Data Index: 859254 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5977. Min Act: -0.0000

Data Index: 939942 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5853. Min Act: -0.0000

Data Index: 731286 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5723. Min Act: -0.0000

Data Index: 339090 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5808. Min Act: -0.0000

Data Index: 35354 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1009785 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1299409 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1083344 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1573449 (Python Code)

Max Activating Token Index: 725

Text #13

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1125029 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5254. Min Act: -0.0000

Data Index: 38508 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1180490 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5291. Min Act: -0.0000

Data Index: 229147 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5293. Min Act: -0.0000

Data Index: 847916 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5230. Min Act: -0.0000

Data Index: 886507 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5255. Min Act: -0.0000

Data Index: 871339 (C4 (Web Text))

Max Activating Token Index: 60