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

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

Neuron 686 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: 0.8040. Min Range: -0.8040

Max Act: 0.8040. Min Act: -0.0000

Data Index: 965383 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7376. Min Act: -0.0000

Data Index: 23624 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7540. Min Act: -0.0000

Data Index: 494753 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7124. Min Act: -0.0000

Data Index: 131014 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6646. Min Act: -0.0000

Data Index: 592206 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7119. Min Act: -0.0000

Data Index: 712851 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1309249 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1175071 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6859. Min Act: -0.0000

Data Index: 185691 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6647. Min Act: -0.0000

Data Index: 729309 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1239614 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6640. Min Act: -0.0000

Data Index: 781584 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6450. Min Act: -0.0000

Data Index: 674658 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6391. Min Act: -0.0000

Data Index: 581466 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6529. Min Act: -0.0000

Data Index: 1119175 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6446. Min Act: -0.0000

Data Index: 625709 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6660. Min Act: -0.0000

Data Index: 468205 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6426. Min Act: -0.0000

Data Index: 333565 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6384. Min Act: -0.0000

Data Index: 625901 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6562. Min Act: -0.0000

Data Index: 806782 (C4 (Web Text))

Max Activating Token Index: 934