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

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

Neuron 2372 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2345. Min Range: -1.2345

Max Act: 1.2345. Min Act: -0.0000

Data Index: 938729 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 1.2345. Min Range: -1.2345

Max Act: 1.0031. Min Act: -0.0000

Data Index: 305870 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.9670. Min Act: -0.0000

Data Index: 149455 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.8484. Min Act: -0.0000

Data Index: 458932 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.8818. Min Act: -0.0000

Data Index: 810156 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.8791. Min Act: -0.0000

Data Index: 747875 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.8164. Min Act: -0.0000

Data Index: 301025 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.8902. Min Act: -0.0000

Data Index: 765352 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1136781 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.8148. Min Act: -0.0000

Data Index: 650301 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.8037. Min Act: -0.0000

Data Index: 629773 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.7826. Min Act: -0.0000

Data Index: 403636 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.7837. Min Act: -0.0000

Data Index: 1159163 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.7107. Min Act: -0.0000

Data Index: 657545 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1134201 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1062612 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.6439. Min Act: -0.0000

Data Index: 908297 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.6466. Min Act: -0.0000

Data Index: 670828 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1079831 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 1.2345. Min Range: -1.2345

Max Act: 0.6118. Min Act: -0.0000

Data Index: 192830 (C4 (Web Text))

Max Activating Token Index: 576