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

Dataset: The Pile

Neuron 239 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8259. Min Range: -4.8259

Max Act: 4.8259. Min Act: -0.0000

Data Index: 1210824 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 4.8259. Min Range: -4.8259

Max Act: 4.2643. Min Act: -0.0000

Data Index: 867217 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.7775. Min Act: -0.0000

Data Index: 1696788 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.8561. Min Act: -0.0000

Data Index: 1552193 (The Pile)

Max Activating Token Index: 637

Text #4

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.4692. Min Act: -0.0000

Data Index: 555665 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.2190. Min Act: -0.0000

Data Index: 1308553 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.3528. Min Act: -0.0000

Data Index: 1083418 (The Pile)

Max Activating Token Index: 237

Text #7

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.3167. Min Act: -0.0000

Data Index: 1760397 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.3149. Min Act: -0.0000

Data Index: 1634717 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.2722. Min Act: -0.0000

Data Index: 791392 (The Pile)

Max Activating Token Index: 978

Text #10

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.2667. Min Act: -0.0000

Data Index: 417064 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.1210. Min Act: -0.0000

Data Index: 24747 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.3966. Min Act: -0.0000

Data Index: 1464747 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.2317. Min Act: -0.0000

Data Index: 1840428 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.3995. Min Act: -0.0000

Data Index: 402175 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.2447. Min Act: -0.0000

Data Index: 1421379 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.0908. Min Act: -0.0000

Data Index: 998389 (The Pile)

Max Activating Token Index: 526

Text #17

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.3287. Min Act: -0.0000

Data Index: 1090701 (The Pile)

Max Activating Token Index: 290

Text #18

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.3058. Min Act: -0.0000

Data Index: 1854492 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 4.8259. Min Range: -4.8259

Max Act: 3.2746. Min Act: -0.0000

Data Index: 1669049 (The Pile)

Max Activating Token Index: 361