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

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

Neuron 4481 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: 1.1260. Min Range: -1.1260

Max Act: 1.1260. Min Act: -0.0000

Data Index: 798841 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.9335. Min Act: -0.0000

Data Index: 543030 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7914. Min Act: -0.0000

Data Index: 763575 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7502. Min Act: -0.0000

Data Index: 770181 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7696. Min Act: -0.0000

Data Index: 413001 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7867. Min Act: -0.0000

Data Index: 531640 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1100630 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.6776. Min Act: -0.0000

Data Index: 664028 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7429. Min Act: -0.0000

Data Index: 227611 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.6703. Min Act: -0.0000

Data Index: 720696 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.6818. Min Act: -0.0000

Data Index: 455302 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1345652 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7107. Min Act: -0.0000

Data Index: 755394 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.7052. Min Act: -0.0000

Data Index: 561601 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.6100. Min Act: -0.0000

Data Index: 765011 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1104370 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.6211. Min Act: -0.0000

Data Index: 957260 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.5833. Min Act: -0.0000

Data Index: 450641 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.6247. Min Act: -0.0000

Data Index: 628641 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.1260. Min Range: -1.1260

Max Act: 0.6270. Min Act: -0.0000

Data Index: 848669 (C4 (Web Text))

Max Activating Token Index: 7