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

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

Neuron 716 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7390. Min Range: -2.7390

Max Act: 2.7390. Min Act: -0.0000

Data Index: 482239 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 2.7390. Min Range: -2.7390

Max Act: 2.6100. Min Act: -0.0000

Data Index: 556932 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 2.7390. Min Range: -2.7390

Max Act: 2.3076. Min Act: -0.0000

Data Index: 894427 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 2.7390. Min Range: -2.7390

Max Act: 2.2610. Min Act: -0.0000

Data Index: 955862 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 2.7390. Min Range: -2.7390

Max Act: 2.1603. Min Act: -0.0000

Data Index: 790501 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 2.7390. Min Range: -2.7390

Max Act: 2.2141. Min Act: -0.0000

Data Index: 1032312 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 2.7390. Min Range: -2.7390

Max Act: 1.9995. Min Act: -0.0000

Data Index: 177571 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 2.7390. Min Range: -2.7390

Max Act: 2.1823. Min Act: -0.0000

Data Index: 1198502 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 2.7390. Min Range: -2.7390

Max Act: 1.8360. Min Act: -0.0000

Data Index: 1005748 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 2.7390. Min Range: -2.7390

Max Act: 1.7928. Min Act: -0.0000

Data Index: 270004 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 2.7390. Min Range: -2.7390

Max Act: 1.8066. Min Act: -0.0000

Data Index: 339750 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 2.7390. Min Range: -2.7390

Max Act: 1.7891. Min Act: -0.0000

Data Index: 28332 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 2.7390. Min Range: -2.7390

Max Act: 1.7657. Min Act: -0.0000

Data Index: 66350 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 2.7390. Min Range: -2.7390

Max Act: 1.6581. Min Act: -0.0000

Data Index: 49286 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 2.7390. Min Range: -2.7390

Max Act: 1.7447. Min Act: -0.0000

Data Index: 80200 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 2.7390. Min Range: -2.7390

Max Act: 1.8388. Min Act: -0.0000

Data Index: 69708 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 2.7390. Min Range: -2.7390

Max Act: 1.7259. Min Act: -0.0000

Data Index: 667974 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 2.7390. Min Range: -2.7390

Max Act: 1.8203. Min Act: -0.0000

Data Index: 294128 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 2.7390. Min Range: -2.7390

Max Act: 1.8237. Min Act: -0.0000

Data Index: 601805 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 2.7390. Min Range: -2.7390

Max Act: 1.7173. Min Act: -0.0000

Data Index: 781905 (C4 (Web Text))

Max Activating Token Index: 249