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

Dataset: The Pile

Neuron 179 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: 1.7555. Min Range: -1.7555

Max Act: 1.7555. Min Act: -0.0000

Data Index: 789910 (The Pile)

Max Activating Token Index: 1007

Text #1

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.6923. Min Act: -0.0000

Data Index: 427163 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.5309. Min Act: -0.0000

Data Index: 394330 (The Pile)

Max Activating Token Index: 982

Text #3

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.6319. Min Act: -0.0000

Data Index: 1053628 (The Pile)

Max Activating Token Index: 975

Text #4

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.5701. Min Act: -0.0000

Data Index: 1440518 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.5570. Min Act: -0.0000

Data Index: 1281686 (The Pile)

Max Activating Token Index: 845

Text #6

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.4911. Min Act: -0.0000

Data Index: 1080518 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.4421. Min Act: -0.0000

Data Index: 850156 (The Pile)

Max Activating Token Index: 767

Text #8

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.5208. Min Act: -0.0000

Data Index: 804152 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.4353. Min Act: -0.0000

Data Index: 1527149 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.5091. Min Act: -0.0000

Data Index: 727112 (The Pile)

Max Activating Token Index: 56

Text #11

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.4516. Min Act: -0.0000

Data Index: 1223278 (The Pile)

Max Activating Token Index: 951

Text #12

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.5425. Min Act: -0.0000

Data Index: 464392 (The Pile)

Max Activating Token Index: 647

Text #13

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.5038. Min Act: -0.0000

Data Index: 814310 (The Pile)

Max Activating Token Index: 80

Text #14

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.4566. Min Act: -0.0000

Data Index: 1639132 (The Pile)

Max Activating Token Index: 970

Text #15

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.4804. Min Act: -0.0000

Data Index: 713700 (The Pile)

Max Activating Token Index: 936

Text #16

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.3621. Min Act: -0.0000

Data Index: 527230 (The Pile)

Max Activating Token Index: 829

Text #17

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.4859. Min Act: -0.0000

Data Index: 975931 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.5267. Min Act: -0.0000

Data Index: 1244883 (The Pile)

Max Activating Token Index: 994

Text #19

Max Range: 1.7555. Min Range: -1.7555

Max Act: 1.4387. Min Act: -0.0000

Data Index: 1629321 (The Pile)

Max Activating Token Index: 432