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

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

Neuron 2425 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0516. Min Range: -1.0516

Max Act: 1.0357. Min Act: -0.0000

Data Index: 906151 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 1.0516. Min Range: -1.0516

Max Act: 1.0516. Min Act: -0.0000

Data Index: 112697 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8909. Min Act: 0.0002

Data Index: 1213286 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8860. Min Act: -0.0000

Data Index: 601603 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8558. Min Act: -0.0000

Data Index: 520297 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7581. Min Act: -0.0000

Data Index: 158950 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8050. Min Act: 0.0002

Data Index: 1193445 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.8384. Min Act: -0.0000

Data Index: 367155 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7673. Min Act: -0.0000

Data Index: 577419 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7453. Min Act: 0.0001

Data Index: 1339421 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6984. Min Act: -0.0000

Data Index: 143198 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7143. Min Act: -0.0000

Data Index: 635006 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7117. Min Act: 0.0001

Data Index: 1140825 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6780. Min Act: -0.0000

Data Index: 104171 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6961. Min Act: 0.0002

Data Index: 515261 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7173. Min Act: -0.0000

Data Index: 54148 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7058. Min Act: 0.0000

Data Index: 24352 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.7061. Min Act: 0.0000

Data Index: 1295387 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6751. Min Act: 0.0002

Data Index: 614729 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 1.0516. Min Range: -1.0516

Max Act: 0.6520. Min Act: 0.0001

Data Index: 77987 (C4 (Web Text))

Max Activating Token Index: 218