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

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

Neuron 3938 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1327645 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5529. Min Act: -0.0000

Data Index: 532331 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5813. Min Act: -0.0000

Data Index: 471224 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5268. Min Act: -0.0000

Data Index: 686661 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5541. Min Act: -0.0000

Data Index: 501180 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5492. Min Act: -0.0000

Data Index: 984127 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4986. Min Act: -0.0000

Data Index: 670637 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1291979 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4898. Min Act: -0.0000

Data Index: 862099 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5078. Min Act: -0.0000

Data Index: 760267 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1227000 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5023. Min Act: -0.0000

Data Index: 756309 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4927. Min Act: -0.0000

Data Index: 497010 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5007. Min Act: -0.0000

Data Index: 39985 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4977. Min Act: 0.0000

Data Index: 586676 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4982. Min Act: 0.0000

Data Index: 766191 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1230815 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1071328 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4545. Min Act: -0.0000

Data Index: 341013 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4521. Min Act: -0.0000

Data Index: 176041 (C4 (Web Text))

Max Activating Token Index: 235