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

Dataset: The Pile

Neuron 2257 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: 1.8721. Min Range: -1.8721

Max Act: 1.8721. Min Act: -0.0000

Data Index: 678977 (The Pile)

Max Activating Token Index: 709

Text #1

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.7226. Min Act: -0.0000

Data Index: 387568 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.5069. Min Act: -0.0000

Data Index: 1360681 (The Pile)

Max Activating Token Index: 938

Text #3

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.5205. Min Act: -0.0000

Data Index: 608968 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.5136. Min Act: -0.0000

Data Index: 1222626 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.4391. Min Act: -0.0000

Data Index: 1564854 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.3852. Min Act: -0.0000

Data Index: 365815 (The Pile)

Max Activating Token Index: 838

Text #7

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.3856. Min Act: -0.0000

Data Index: 461560 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.3886. Min Act: -0.0000

Data Index: 332750 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.3662. Min Act: -0.0000

Data Index: 1659698 (The Pile)

Max Activating Token Index: 337

Text #10

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.3599. Min Act: -0.0000

Data Index: 231551 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.3372. Min Act: -0.0000

Data Index: 511329 (The Pile)

Max Activating Token Index: 346

Text #12

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1378988 (The Pile)

Max Activating Token Index: 586

Text #13

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.3858. Min Act: -0.0000

Data Index: 1008239 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.2215. Min Act: -0.0000

Data Index: 1995539 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.2194. Min Act: -0.0000

Data Index: 1149037 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.2851. Min Act: -0.0000

Data Index: 172102 (The Pile)

Max Activating Token Index: 166

Text #17

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.2567. Min Act: -0.0000

Data Index: 776047 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.2802. Min Act: -0.0000

Data Index: 1835090 (The Pile)

Max Activating Token Index: 319

Text #19

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.2706. Min Act: -0.0000

Data Index: 88074 (The Pile)

Max Activating Token Index: 356