Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3476 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1086. Min Range: -1.1086

Max Act: 1.1086. Min Act: -0.0000

Data Index: 385471 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 1.1086. Min Range: -1.1086

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1079916 (The Pile)

Max Activating Token Index: 695

Text #2

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1512134 (The Pile)

Max Activating Token Index: 175

Text #3

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8406. Min Act: -0.0000

Data Index: 84702 (The Pile)

Max Activating Token Index: 978

Text #4

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7736. Min Act: -0.0000

Data Index: 1170999 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1745906 (The Pile)

Max Activating Token Index: 673

Text #6

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1450013 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1849493 (The Pile)

Max Activating Token Index: 704

Text #8

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1062269 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7968. Min Act: -0.0000

Data Index: 889749 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7680. Min Act: -0.0000

Data Index: 448906 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1368958 (The Pile)

Max Activating Token Index: 882

Text #12

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1782037 (The Pile)

Max Activating Token Index: 584

Text #13

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8096. Min Act: -0.0000

Data Index: 553577 (The Pile)

Max Activating Token Index: 678

Text #14

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7660. Min Act: -0.0000

Data Index: 187179 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1964946 (The Pile)

Max Activating Token Index: 776

Text #16

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7633. Min Act: -0.0000

Data Index: 964012 (The Pile)

Max Activating Token Index: 181

Text #17

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8036. Min Act: -0.0000

Data Index: 551095 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7444. Min Act: -0.0000

Data Index: 1643063 (The Pile)

Max Activating Token Index: 310

Text #19

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7426. Min Act: -0.0000

Data Index: 419662 (The Pile)

Max Activating Token Index: 529