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

Dataset: The Pile

Neuron 3281 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: 0.8721. Min Range: -0.8721

Max Act: 0.8615. Min Act: -0.0000

Data Index: 519834 (The Pile)

Max Activating Token Index: 467

Text #1

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1622088 (The Pile)

Max Activating Token Index: 681

Text #2

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1361341 (The Pile)

Max Activating Token Index: 113

Text #3

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1462643 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1249058 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.7379. Min Act: -0.0000

Data Index: 87346 (The Pile)

Max Activating Token Index: 531

Text #6

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1210187 (The Pile)

Max Activating Token Index: 85

Text #7

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1380208 (The Pile)

Max Activating Token Index: 333

Text #8

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6686. Min Act: -0.0000

Data Index: 478981 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1364881 (The Pile)

Max Activating Token Index: 507

Text #10

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.7078. Min Act: -0.0000

Data Index: 702603 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.7251. Min Act: -0.0000

Data Index: 949111 (The Pile)

Max Activating Token Index: 282

Text #12

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1836823 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.7144. Min Act: -0.0000

Data Index: 1781694 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6774. Min Act: -0.0000

Data Index: 314553 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.7039. Min Act: -0.0000

Data Index: 521822 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1395009 (The Pile)

Max Activating Token Index: 43

Text #17

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1683515 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1871342 (The Pile)

Max Activating Token Index: 733

Text #19

Max Range: 0.8721. Min Range: -0.8721

Max Act: 0.6228. Min Act: -0.0000

Data Index: 725920 (The Pile)

Max Activating Token Index: 167