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

Dataset: The Pile

Neuron 3852 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: 1.6188. Min Range: -1.6188

Max Act: 1.6188. Min Act: -0.0000

Data Index: 642175 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.4498. Min Act: -0.0000

Data Index: 1589720 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.4537. Min Act: -0.0000

Data Index: 1861576 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.4983. Min Act: -0.0000

Data Index: 541523 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3193. Min Act: -0.0000

Data Index: 70386 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3915. Min Act: -0.0000

Data Index: 422306 (The Pile)

Max Activating Token Index: 239

Text #6

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3019. Min Act: -0.0000

Data Index: 798715 (The Pile)

Max Activating Token Index: 843

Text #7

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1732712 (The Pile)

Max Activating Token Index: 847

Text #8

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3687. Min Act: -0.0000

Data Index: 512097 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3130. Min Act: -0.0000

Data Index: 572869 (The Pile)

Max Activating Token Index: 725

Text #10

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3974. Min Act: -0.0000

Data Index: 1604813 (The Pile)

Max Activating Token Index: 268

Text #11

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.3014. Min Act: -0.0000

Data Index: 618729 (The Pile)

Max Activating Token Index: 944

Text #12

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.2847. Min Act: -0.0000

Data Index: 1690283 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.2764. Min Act: -0.0000

Data Index: 1424526 (The Pile)

Max Activating Token Index: 808

Text #14

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.2079. Min Act: -0.0000

Data Index: 83593 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.2728. Min Act: -0.0000

Data Index: 1192372 (The Pile)

Max Activating Token Index: 372

Text #16

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.2715. Min Act: -0.0000

Data Index: 1731154 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.1844. Min Act: -0.0000

Data Index: 945793 (The Pile)

Max Activating Token Index: 695

Text #18

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.1540. Min Act: -0.0000

Data Index: 853268 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.2365. Min Act: -0.0000

Data Index: 551605 (The Pile)

Max Activating Token Index: 120