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

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

Neuron 2969 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.8109. Min Act: -0.0001

Data Index: 1236113 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.7544. Min Act: -0.0000

Data Index: 43419 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6045. Min Act: -0.0001

Data Index: 1058456 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6441. Min Act: -0.0000

Data Index: 1095257 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.6387. Min Act: -0.0000

Data Index: 424687 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.4782. Min Act: -0.0000

Data Index: 126123 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.5746. Min Act: -0.0000

Data Index: 850630 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.3553. Min Act: -0.0000

Data Index: 1079627 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.1694. Min Act: -0.0000

Data Index: 734194 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.0219. Min Act: -0.0001

Data Index: 1068424 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.2821. Min Act: -0.0000

Data Index: 794652 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 3.8109. Min Range: -3.8109

Max Act: 2.9936. Min Act: -0.0000

Data Index: 527746 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.0035. Min Act: -0.0000

Data Index: 1181577 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.1003. Min Act: -0.0000

Data Index: 1288153 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.0441. Min Act: -0.0001

Data Index: 903839 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.0350. Min Act: -0.0000

Data Index: 1331362 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 3.8109. Min Range: -3.8109

Max Act: 2.9925. Min Act: -0.0000

Data Index: 719149 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.1829. Min Act: -0.0000

Data Index: 295584 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 3.8109. Min Range: -3.8109

Max Act: 2.8822. Min Act: -0.0000

Data Index: 765263 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 3.8109. Min Range: -3.8109

Max Act: 3.0156. Min Act: -0.0000

Data Index: 804673 (C4 (Web Text))

Max Activating Token Index: 687