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

Dataset: The Pile

Neuron 263 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0684. Min Act: -0.0000

Data Index: 979585 (The Pile)

Max Activating Token Index: 186

Text #1

Max Range: 1.0830. Min Range: -1.0830

Max Act: 1.0830. Min Act: 0.0000

Data Index: 1742046 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.9331. Min Act: -0.0000

Data Index: 1732671 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.9796. Min Act: 0.0000

Data Index: 1079698 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.9720. Min Act: 0.0000

Data Index: 3125 (The Pile)

Max Activating Token Index: 335

Text #5

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.9152. Min Act: 0.0000

Data Index: 1584592 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1801685 (The Pile)

Max Activating Token Index: 451

Text #7

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1315799 (The Pile)

Max Activating Token Index: 485

Text #8

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.7583. Min Act: 0.0000

Data Index: 1996770 (The Pile)

Max Activating Token Index: 26

Text #9

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.8129. Min Act: -0.0000

Data Index: 1704262 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1737664 (The Pile)

Max Activating Token Index: 152

Text #11

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1382499 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1353897 (The Pile)

Max Activating Token Index: 366

Text #13

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.9146. Min Act: -0.0000

Data Index: 1142767 (The Pile)

Max Activating Token Index: 385

Text #14

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1282493 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1518788 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1537190 (The Pile)

Max Activating Token Index: 27

Text #17

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1291795 (The Pile)

Max Activating Token Index: 492

Text #18

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1793772 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 1.0830. Min Range: -1.0830

Max Act: 0.7135. Min Act: 0.0000

Data Index: 243172 (The Pile)

Max Activating Token Index: 406