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

Dataset: The Pile

Neuron 4972 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.5812. Min Act: -0.0000

Data Index: 253621 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.5475. Min Act: -0.0000

Data Index: 493318 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.2438. Min Act: -0.0000

Data Index: 132892 (The Pile)

Max Activating Token Index: 98

Text #3

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.4716. Min Act: -0.0000

Data Index: 327601 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.4105. Min Act: -0.0000

Data Index: 201710 (The Pile)

Max Activating Token Index: 272

Text #5

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.4794. Min Act: -0.0000

Data Index: 322076 (The Pile)

Max Activating Token Index: 253

Text #6

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.3462. Min Act: -0.0000

Data Index: 134933 (The Pile)

Max Activating Token Index: 279

Text #7

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.3153. Min Act: -0.0000

Data Index: 1438765 (The Pile)

Max Activating Token Index: 361

Text #8

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.2948. Min Act: -0.0000

Data Index: 45142 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.2992. Min Act: -0.0000

Data Index: 710040 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.2686. Min Act: -0.0000

Data Index: 230200 (The Pile)

Max Activating Token Index: 250

Text #11

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.2560. Min Act: -0.0000

Data Index: 988132 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.2214. Min Act: -0.0000

Data Index: 586607 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1865799 (The Pile)

Max Activating Token Index: 488

Text #14

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.1793. Min Act: -0.0000

Data Index: 1737577 (The Pile)

Max Activating Token Index: 579

Text #15

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.1672. Min Act: -0.0000

Data Index: 1386533 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1997407 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1903458 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.2174. Min Act: -0.0000

Data Index: 1457239 (The Pile)

Max Activating Token Index: 91

Text #19

Max Range: 1.5812. Min Range: -1.5812

Max Act: 1.1438. Min Act: -0.0000

Data Index: 1639550 (The Pile)

Max Activating Token Index: 721