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

Dataset: The Pile

Neuron 1506 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1580279 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1451501 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1645607 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1682432 (The Pile)

Max Activating Token Index: 401

Text #4

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.7532. Min Act: -0.0000

Data Index: 597002 (The Pile)

Max Activating Token Index: 386

Text #5

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.7012. Min Act: -0.0000

Data Index: 31970 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6941. Min Act: -0.0000

Data Index: 241325 (The Pile)

Max Activating Token Index: 370

Text #7

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1183568 (The Pile)

Max Activating Token Index: 577

Text #8

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6118. Min Act: -0.0000

Data Index: 705699 (The Pile)

Max Activating Token Index: 316

Text #9

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6073. Min Act: -0.0000

Data Index: 227811 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1970376 (The Pile)

Max Activating Token Index: 270

Text #11

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1702389 (The Pile)

Max Activating Token Index: 340

Text #12

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5648. Min Act: 0.0000

Data Index: 608079 (The Pile)

Max Activating Token Index: 131

Text #13

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1359530 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5532. Min Act: -0.0000

Data Index: 106245 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1847290 (The Pile)

Max Activating Token Index: 349

Text #16

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5452. Min Act: 0.0000

Data Index: 1581947 (The Pile)

Max Activating Token Index: 341

Text #17

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1800214 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1345109 (The Pile)

Max Activating Token Index: 99

Text #19

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5302. Min Act: 0.0000

Data Index: 1757390 (The Pile)

Max Activating Token Index: 44