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

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

Neuron 5650 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: 1.2015. Min Range: -1.2015

Max Act: 1.2015. Min Act: -0.0000

Data Index: 1294216 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.0714. Min Act: -0.0000

Data Index: 430427 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.1406. Min Act: -0.0000

Data Index: 588623 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.1083. Min Act: -0.0000

Data Index: 614901 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.0234. Min Act: -0.0000

Data Index: 650860 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9991. Min Act: -0.0000

Data Index: 477059 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.0525. Min Act: -0.0000

Data Index: 564847 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9417. Min Act: -0.0000

Data Index: 494004 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.0018. Min Act: -0.0000

Data Index: 56289 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 1.2015. Min Range: -1.2015

Max Act: 1.0492. Min Act: -0.0000

Data Index: 568495 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9122. Min Act: -0.0000

Data Index: 292921 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9027. Min Act: -0.0000

Data Index: 43853 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1041650 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.9616. Min Act: -0.0000

Data Index: 37482 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1140424 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.8723. Min Act: -0.0000

Data Index: 298054 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.8110. Min Act: -0.0000

Data Index: 507977 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.8389. Min Act: -0.0000

Data Index: 207077 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.8642. Min Act: -0.0000

Data Index: 935811 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 1.2015. Min Range: -1.2015

Max Act: 0.8269. Min Act: -0.0000

Data Index: 781404 (C4 (Web Text))

Max Activating Token Index: 587