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

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

Neuron 2692 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1264. Min Act: -0.0001

Data Index: 339506 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1209. Min Act: -0.0000

Data Index: 584515 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1160. Min Act: -0.0001

Data Index: 739446 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1194. Min Act: -0.0001

Data Index: 536330 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1046. Min Act: -0.0001

Data Index: 583604 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1034. Min Act: -0.0001

Data Index: 400299 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0984. Min Act: -0.0001

Data Index: 948899 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1011. Min Act: -0.0001

Data Index: 465212 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1004. Min Act: -0.0000

Data Index: 316902 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1313293 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0950. Min Act: -0.0001

Data Index: 876874 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0932. Min Act: -0.0000

Data Index: 270109 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0863. Min Act: -0.0001

Data Index: 601433 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0878. Min Act: -0.0000

Data Index: 874169 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0853. Min Act: -0.0000

Data Index: 649443 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0794. Min Act: -0.0001

Data Index: 717775 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0841. Min Act: -0.0001

Data Index: 1118713 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1194309 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0841. Min Act: -0.0001

Data Index: 1086609 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0827. Min Act: -0.0001

Data Index: 407515 (C4 (Web Text))

Max Activating Token Index: 759