Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4023 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.7323. Min Act: -0.0002

Data Index: 433197 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.6670. Min Act: -0.0002

Data Index: 1086428 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.6819. Min Act: -0.0002

Data Index: 655555 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.6312. Min Act: -0.0002

Data Index: 156118 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5991. Min Act: -0.0002

Data Index: 900932 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5886. Min Act: -0.0002

Data Index: 371964 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5733. Min Act: -0.0002

Data Index: 719747 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5560. Min Act: -0.0002

Data Index: 1097354 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5531. Min Act: -0.0002

Data Index: 184706 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5387. Min Act: -0.0002

Data Index: 9844 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5243. Min Act: -0.0002

Data Index: 712992 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5397. Min Act: -0.0002

Data Index: 900146 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5401. Min Act: -0.0002

Data Index: 1207529 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5380. Min Act: -0.0002

Data Index: 340997 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4992. Min Act: -0.0002

Data Index: 731875 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5364. Min Act: -0.0002

Data Index: 633844 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4960. Min Act: -0.0002

Data Index: 484093 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5080. Min Act: -0.0002

Data Index: 976216 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5023. Min Act: -0.0002

Data Index: 239177 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4859. Min Act: -0.0002

Data Index: 744885 (C4 (Web Text))

Max Activating Token Index: 235