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

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

Neuron 1759 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.9095. Min Act: -0.0001

Data Index: 693642 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8960. Min Act: -0.0001

Data Index: 778038 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8788. Min Act: -0.0001

Data Index: 1218024 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7616. Min Act: -0.0001

Data Index: 1135813 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.8948. Min Act: -0.0001

Data Index: 488139 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7530. Min Act: -0.0001

Data Index: 1357685 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7123. Min Act: -0.0001

Data Index: 1310143 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7157. Min Act: -0.0001

Data Index: 24911 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7955. Min Act: -0.0001

Data Index: 1243977 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7873. Min Act: -0.0001

Data Index: 66383 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.6882. Min Act: -0.0001

Data Index: 1088743 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7706. Min Act: -0.0001

Data Index: 806887 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7993. Min Act: -0.0001

Data Index: 1335679 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7645. Min Act: -0.0001

Data Index: 567066 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7086. Min Act: -0.0001

Data Index: 1066708 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.5833. Min Act: -0.0001

Data Index: 1231963 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.7373. Min Act: -0.0001

Data Index: 237499 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1078762 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.6333. Min Act: -0.0001

Data Index: 773437 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.9095. Min Range: -0.9095

Max Act: 0.6989. Min Act: -0.0001

Data Index: 11683 (C4 (Web Text))

Max Activating Token Index: 191