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

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

Neuron 171 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.5634. Min Act: -0.0000

Data Index: 293337 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.5134. Min Act: -0.0000

Data Index: 734895 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.5154. Min Act: -0.0000

Data Index: 338615 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4952. Min Act: -0.0000

Data Index: 620311 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4896. Min Act: -0.0000

Data Index: 1189693 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4789. Min Act: -0.0000

Data Index: 979806 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4952. Min Act: -0.0000

Data Index: 120198 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4618. Min Act: -0.0000

Data Index: 237490 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4751. Min Act: -0.0000

Data Index: 908108 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4901. Min Act: -0.0000

Data Index: 261104 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1189209 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4764. Min Act: -0.0000

Data Index: 6649 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4623. Min Act: -0.0000

Data Index: 515960 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4449. Min Act: -0.0000

Data Index: 504670 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1107001 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4498. Min Act: -0.0000

Data Index: 301068 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4492. Min Act: -0.0000

Data Index: 393801 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4429. Min Act: -0.0000

Data Index: 598764 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4451. Min Act: -0.0000

Data Index: 126783 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1017790 (C4 (Web Text))

Max Activating Token Index: 398