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

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

Neuron 2225 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2109. Min Range: -1.2109

Max Act: 1.0651. Min Act: -0.0002

Data Index: 1355043 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 1.2109. Min Range: -1.2109

Max Act: 1.2109. Min Act: -0.0002

Data Index: 985577 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8987. Min Act: -0.0002

Data Index: 1335350 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8982. Min Act: -0.0002

Data Index: 917012 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8024. Min Act: -0.0002

Data Index: 707378 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8041. Min Act: -0.0002

Data Index: 151681 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8043. Min Act: -0.0002

Data Index: 166305 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8032. Min Act: -0.0002

Data Index: 794478 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8391. Min Act: -0.0002

Data Index: 1099920 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8238. Min Act: -0.0002

Data Index: 653073 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.9072. Min Act: -0.0002

Data Index: 388135 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8328. Min Act: -0.0002

Data Index: 370308 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.9151. Min Act: -0.0002

Data Index: 1126278 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.7335. Min Act: -0.0002

Data Index: 710254 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.7793. Min Act: -0.0002

Data Index: 455540 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8048. Min Act: -0.0002

Data Index: 256734 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.7287. Min Act: -0.0002

Data Index: 942083 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.7330. Min Act: -0.0002

Data Index: 555802 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.7124. Min Act: -0.0002

Data Index: 1240490 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.7297. Min Act: -0.0003

Data Index: 576300 (C4 (Web Text))

Max Activating Token Index: 282