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

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

Neuron 1897 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.6344. Min Act: -0.0000

Data Index: 665768 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.6320. Min Act: -0.0000

Data Index: 975923 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.6116. Min Act: -0.0000

Data Index: 435854 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5524. Min Act: -0.0000

Data Index: 732266 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5786. Min Act: -0.0000

Data Index: 208245 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5750. Min Act: -0.0000

Data Index: 380418 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5564. Min Act: -0.0000

Data Index: 963411 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5882. Min Act: -0.0000

Data Index: 242219 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5477. Min Act: -0.0000

Data Index: 899148 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1026604 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5203. Min Act: -0.0000

Data Index: 462189 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5075. Min Act: -0.0000

Data Index: 513515 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1148789 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4966. Min Act: -0.0000

Data Index: 207557 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5247. Min Act: -0.0000

Data Index: 720796 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5112. Min Act: -0.0000

Data Index: 952446 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5047. Min Act: -0.0000

Data Index: 519106 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5681. Min Act: -0.0000

Data Index: 396902 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1008240 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4885. Min Act: -0.0000

Data Index: 914069 (C4 (Web Text))

Max Activating Token Index: 31