Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3859 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.8285. Min Act: -0.0001

Data Index: 249848 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.8006. Min Act: -0.0001

Data Index: 713038 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.7642. Min Act: -0.0001

Data Index: 1140076 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.7736. Min Act: -0.0001

Data Index: 625854 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.6372. Min Act: -0.0001

Data Index: 269286 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.6072. Min Act: -0.0001

Data Index: 330993 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.6510. Min Act: -0.0001

Data Index: 1246377 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.5806. Min Act: -0.0001

Data Index: 932191 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.6613. Min Act: -0.0001

Data Index: 1207857 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.6099. Min Act: -0.0001

Data Index: 1309895 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.5908. Min Act: -0.0001

Data Index: 808809 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.5234. Min Act: -0.0001

Data Index: 1168679 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.4896. Min Act: -0.0001

Data Index: 418735 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.5864. Min Act: -0.0001

Data Index: 559807 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.5007. Min Act: -0.0001

Data Index: 527156 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.3986. Min Act: -0.0001

Data Index: 655128 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.5657. Min Act: -0.0001

Data Index: 62108 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.5201. Min Act: -0.0001

Data Index: 905974 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.5709. Min Act: -0.0001

Data Index: 1266739 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 1.8285. Min Range: -1.8285

Max Act: 1.5499. Min Act: -0.0001

Data Index: 955746 (C4 (Web Text))

Max Activating Token Index: 160