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

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

Neuron 857 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0807. Min Range: -1.0807

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1304543 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 1.0807. Min Range: -1.0807

Max Act: 1.0484. Min Act: -0.0000

Data Index: 974321 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.0807. Min Range: -1.0807

Max Act: 1.0013. Min Act: -0.0000

Data Index: 1340695 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9734. Min Act: -0.0000

Data Index: 346772 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1310694 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9217. Min Act: -0.0000

Data Index: 235582 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9073. Min Act: -0.0000

Data Index: 214285 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8922. Min Act: -0.0000

Data Index: 553321 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8618. Min Act: -0.0000

Data Index: 740919 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8783. Min Act: -0.0000

Data Index: 2914 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9021. Min Act: -0.0000

Data Index: 364538 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1160922 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8214. Min Act: -0.0000

Data Index: 484412 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8160. Min Act: -0.0000

Data Index: 341121 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1330276 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9015. Min Act: -0.0000

Data Index: 674434 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.6611. Min Act: -0.0000

Data Index: 833724 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.7605. Min Act: -0.0000

Data Index: 94888 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1008133 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.7723. Min Act: -0.0000

Data Index: 509188 (C4 (Web Text))

Max Activating Token Index: 442