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

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

Neuron 844 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8618. Min Range: -2.8618

Max Act: 2.7766. Min Act: -0.0000

Data Index: 755133 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 2.8618. Min Range: -2.8618

Max Act: 2.8618. Min Act: -0.0000

Data Index: 727035 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.7871. Min Act: -0.0000

Data Index: 125520 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.7404. Min Act: -0.0000

Data Index: 606838 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.6921. Min Act: -0.0000

Data Index: 703658 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.7563. Min Act: -0.0000

Data Index: 329482 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.7266. Min Act: -0.0000

Data Index: 601366 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.7171. Min Act: -0.0000

Data Index: 863769 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.6761. Min Act: -0.0000

Data Index: 1283490 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.7037. Min Act: -0.0000

Data Index: 475408 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.4670. Min Act: -0.0000

Data Index: 400549 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.5380. Min Act: -0.0000

Data Index: 696323 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.5396. Min Act: -0.0000

Data Index: 876148 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.5927. Min Act: -0.0000

Data Index: 989239 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.4223. Min Act: -0.0000

Data Index: 223318 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.4304. Min Act: -0.0000

Data Index: 1205188 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.5764. Min Act: -0.0000

Data Index: 450873 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.5632. Min Act: -0.0000

Data Index: 1047674 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.4739. Min Act: -0.0000

Data Index: 350355 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 2.8618. Min Range: -2.8618

Max Act: 1.4538. Min Act: -0.0000

Data Index: 1316300 (C4 (Web Text))

Max Activating Token Index: 1023