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

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

Neuron 3162 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.5526. Min Act: -0.0002

Data Index: 786853 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.5212. Min Act: -0.0002

Data Index: 953771 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4806. Min Act: -0.0002

Data Index: 590317 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.5149. Min Act: -0.0002

Data Index: 1326321 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4502. Min Act: -0.0002

Data Index: 13567 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.5022. Min Act: -0.0002

Data Index: 1188832 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4841. Min Act: -0.0002

Data Index: 286703 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.5055. Min Act: -0.0002

Data Index: 1181472 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4335. Min Act: -0.0002

Data Index: 105268 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4749. Min Act: -0.0002

Data Index: 1354770 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4634. Min Act: -0.0002

Data Index: 531579 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4781. Min Act: -0.0002

Data Index: 105816 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4682. Min Act: -0.0001

Data Index: 5636 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4821. Min Act: -0.0002

Data Index: 623297 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4900. Min Act: -0.0002

Data Index: 340714 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4723. Min Act: -0.0001

Data Index: 728883 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4479. Min Act: -0.0002

Data Index: 1249229 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.4156. Min Act: -0.0002

Data Index: 898279 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.5013. Min Act: -0.0002

Data Index: 270535 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.5549. Min Range: -0.5549

Max Act: 0.5549. Min Act: -0.0002

Data Index: 964497 (C4 (Web Text))

Max Activating Token Index: 844