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

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

Neuron 3403 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: 1.3257. Min Range: -1.3257

Max Act: 1.3257. Min Act: -0.0001

Data Index: 65219 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.1313. Min Act: -0.0001

Data Index: 1114819 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.1051. Min Act: -0.0001

Data Index: 365932 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.1026. Min Act: -0.0001

Data Index: 529609 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0576. Min Act: -0.0001

Data Index: 874156 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0142. Min Act: -0.0001

Data Index: 949794 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9962. Min Act: -0.0001

Data Index: 533141 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0193. Min Act: -0.0001

Data Index: 521776 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0035. Min Act: -0.0001

Data Index: 218576 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9539. Min Act: -0.0001

Data Index: 319723 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9916. Min Act: -0.0001

Data Index: 597713 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9238. Min Act: -0.0001

Data Index: 1358581 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0110. Min Act: -0.0001

Data Index: 1143943 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9509. Min Act: -0.0001

Data Index: 382040 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9676. Min Act: -0.0001

Data Index: 1274720 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9554. Min Act: -0.0001

Data Index: 683493 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9520. Min Act: -0.0001

Data Index: 461059 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9237. Min Act: -0.0001

Data Index: 1302960 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9781. Min Act: -0.0001

Data Index: 709665 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.8909. Min Act: -0.0001

Data Index: 458856 (C4 (Web Text))

Max Activating Token Index: 828