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

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

Neuron 3512 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.9898. Min Act: -0.0000

Data Index: 289855 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.6089. Min Act: -0.0000

Data Index: 822415 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.6532. Min Act: -0.0000

Data Index: 1276131 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.5752. Min Act: -0.0000

Data Index: 466789 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.8487. Min Act: -0.0000

Data Index: 243479 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.6260. Min Act: -0.0000

Data Index: 803362 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.6074. Min Act: -0.0000

Data Index: 614535 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.5978. Min Act: -0.0000

Data Index: 775817 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.5201. Min Act: -0.0000

Data Index: 576992 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.5233. Min Act: -0.0000

Data Index: 1188850 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.4393. Min Act: -0.0000

Data Index: 574962 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.4246. Min Act: -0.0000

Data Index: 637183 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.4222. Min Act: -0.0000

Data Index: 665629 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.5090. Min Act: -0.0000

Data Index: 904916 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.5130. Min Act: -0.0000

Data Index: 727471 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.3508. Min Act: -0.0000

Data Index: 1049019 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.4999. Min Act: -0.0000

Data Index: 1159208 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.4776. Min Act: -0.0000

Data Index: 93453 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.4551. Min Act: -0.0000

Data Index: 774837 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 1.9898. Min Range: -1.9898

Max Act: 1.4459. Min Act: -0.0000

Data Index: 1011941 (C4 (Web Text))

Max Activating Token Index: 857