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

Dataset: The Pile

Neuron 4462 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.7919. Min Act: -0.0000

Data Index: 1319105 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.8299. Min Act: -0.0000

Data Index: 379243 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.5919. Min Act: -0.0000

Data Index: 820188 (The Pile)

Max Activating Token Index: 383

Text #3

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.3900. Min Act: -0.0000

Data Index: 435721 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.3794. Min Act: -0.0000

Data Index: 1605363 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.1751. Min Act: -0.0000

Data Index: 1682698 (The Pile)

Max Activating Token Index: 877

Text #6

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.4558. Min Act: -0.0000

Data Index: 1801324 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.4463. Min Act: -0.0000

Data Index: 193242 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.4187. Min Act: -0.0000

Data Index: 1754070 (The Pile)

Max Activating Token Index: 341

Text #9

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.3403. Min Act: -0.0000

Data Index: 596264 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.2942. Min Act: -0.0000

Data Index: 567877 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.3709. Min Act: -0.0000

Data Index: 385504 (The Pile)

Max Activating Token Index: 783

Text #12

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.4278. Min Act: -0.0000

Data Index: 758117 (The Pile)

Max Activating Token Index: 211

Text #13

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.3873. Min Act: -0.0000

Data Index: 5010 (The Pile)

Max Activating Token Index: 392

Text #14

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.2579. Min Act: -0.0000

Data Index: 1666835 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.3255. Min Act: -0.0000

Data Index: 1223183 (The Pile)

Max Activating Token Index: 47

Text #16

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.4764. Min Act: -0.0000

Data Index: 1507521 (The Pile)

Max Activating Token Index: 261

Text #17

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.4037. Min Act: -0.0000

Data Index: 712373 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.2608. Min Act: -0.0000

Data Index: 953235 (The Pile)

Max Activating Token Index: 893

Text #19

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.2007. Min Act: -0.0000

Data Index: 640394 (The Pile)

Max Activating Token Index: 416