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

Dataset: The Pile

Neuron 778 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: 0.1316. Min Range: -0.1316

Max Act: 0.1316. Min Act: -0.0000

Data Index: 163906 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1175. Min Act: 0.0000

Data Index: 1499008 (The Pile)

Max Activating Token Index: 659

Text #2

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1149. Min Act: -0.0000

Data Index: 356760 (The Pile)

Max Activating Token Index: 384

Text #3

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1514036 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1158. Min Act: -0.0000

Data Index: 656322 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0945. Min Act: -0.0000

Data Index: 692501 (The Pile)

Max Activating Token Index: 897

Text #6

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0824. Min Act: -0.0000

Data Index: 923400 (The Pile)

Max Activating Token Index: 749

Text #7

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1050. Min Act: -0.0000

Data Index: 1915308 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1015. Min Act: -0.0000

Data Index: 774177 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1411345 (The Pile)

Max Activating Token Index: 692

Text #10

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0960. Min Act: -0.0000

Data Index: 816928 (The Pile)

Max Activating Token Index: 969

Text #11

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0976. Min Act: -0.0000

Data Index: 358958 (The Pile)

Max Activating Token Index: 317

Text #12

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0961. Min Act: -0.0000

Data Index: 179337 (The Pile)

Max Activating Token Index: 632

Text #13

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1785779 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0949. Min Act: -0.0000

Data Index: 718555 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1566645 (The Pile)

Max Activating Token Index: 980

Text #16

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1860850 (The Pile)

Max Activating Token Index: 312

Text #17

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1624668 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1067583 (The Pile)

Max Activating Token Index: 285

Text #19

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0920. Min Act: -0.0000

Data Index: 1389014 (The Pile)

Max Activating Token Index: 309