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

Dataset: The Pile

Neuron 1496 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0022. Min Range: -1.0022

Max Act: 1.0022. Min Act: -0.0000

Data Index: 1766028 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.9181. Min Act: -0.0000

Data Index: 897218 (The Pile)

Max Activating Token Index: 515

Text #2

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.9434. Min Act: -0.0000

Data Index: 441425 (The Pile)

Max Activating Token Index: 268

Text #3

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1588881 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8488. Min Act: -0.0000

Data Index: 407674 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8461. Min Act: -0.0000

Data Index: 168520 (The Pile)

Max Activating Token Index: 888

Text #6

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1358473 (The Pile)

Max Activating Token Index: 10

Text #7

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7849. Min Act: -0.0000

Data Index: 1222987 (The Pile)

Max Activating Token Index: 279

Text #8

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8445. Min Act: -0.0000

Data Index: 350031 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8147. Min Act: -0.0000

Data Index: 553542 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1449253 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8198. Min Act: -0.0000

Data Index: 273986 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7653. Min Act: -0.0000

Data Index: 199118 (The Pile)

Max Activating Token Index: 818

Text #13

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1649849 (The Pile)

Max Activating Token Index: 22

Text #14

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8204. Min Act: -0.0000

Data Index: 464238 (The Pile)

Max Activating Token Index: 202

Text #15

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7784. Min Act: -0.0000

Data Index: 1071388 (The Pile)

Max Activating Token Index: 206

Text #16

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7637. Min Act: -0.0000

Data Index: 490255 (The Pile)

Max Activating Token Index: 914

Text #17

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1644521 (The Pile)

Max Activating Token Index: 401

Text #18

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7816. Min Act: -0.0000

Data Index: 1962951 (The Pile)

Max Activating Token Index: 706

Text #19

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1703359 (The Pile)

Max Activating Token Index: 375