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

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

Neuron 5452 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3637. Min Range: -2.3637

Max Act: 2.3637. Min Act: -0.0000

Data Index: 303451 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 2.3637. Min Range: -2.3637

Max Act: 2.2780. Min Act: -0.0000

Data Index: 323033 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 2.3637. Min Range: -2.3637

Max Act: 2.1471. Min Act: -0.0000

Data Index: 294028 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 2.3637. Min Range: -2.3637

Max Act: 1.9954. Min Act: -0.0000

Data Index: 125065 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 2.3637. Min Range: -2.3637

Max Act: 2.0558. Min Act: -0.0000

Data Index: 458847 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 2.3637. Min Range: -2.3637

Max Act: 1.9581. Min Act: -0.0000

Data Index: 486363 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 2.3637. Min Range: -2.3637

Max Act: 1.9060. Min Act: -0.0000

Data Index: 1146301 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 2.3637. Min Range: -2.3637

Max Act: 2.1136. Min Act: -0.0000

Data Index: 903432 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 2.3637. Min Range: -2.3637

Max Act: 2.0112. Min Act: -0.0000

Data Index: 1089865 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 2.3637. Min Range: -2.3637

Max Act: 1.9332. Min Act: -0.0000

Data Index: 1155314 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 2.3637. Min Range: -2.3637

Max Act: 2.1134. Min Act: -0.0000

Data Index: 58700 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 2.3637. Min Range: -2.3637

Max Act: 1.9620. Min Act: -0.0000

Data Index: 591986 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 2.3637. Min Range: -2.3637

Max Act: 1.9273. Min Act: -0.0000

Data Index: 1208874 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 2.3637. Min Range: -2.3637

Max Act: 1.9199. Min Act: -0.0000

Data Index: 632125 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 2.3637. Min Range: -2.3637

Max Act: 1.8744. Min Act: -0.0000

Data Index: 1619862 (Python Code)

Max Activating Token Index: 553

Text #15

Max Range: 2.3637. Min Range: -2.3637

Max Act: 1.7281. Min Act: -0.0000

Data Index: 489746 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 2.3637. Min Range: -2.3637

Max Act: 1.8150. Min Act: -0.0000

Data Index: 744453 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 2.3637. Min Range: -2.3637

Max Act: 1.7814. Min Act: -0.0000

Data Index: 744768 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 2.3637. Min Range: -2.3637

Max Act: 1.6589. Min Act: -0.0000

Data Index: 1006132 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 2.3637. Min Range: -2.3637

Max Act: 1.7260. Min Act: -0.0000

Data Index: 161087 (C4 (Web Text))

Max Activating Token Index: 425