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

Dataset: The Pile

Neuron 1613 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: 0.4429. Min Range: -0.4429

Max Act: 0.4127. Min Act: -0.0000

Data Index: 206469 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1128726 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1728523 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.4134. Min Act: -0.0000

Data Index: 349800 (The Pile)

Max Activating Token Index: 411

Text #4

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1761569 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1349867 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.4345. Min Act: -0.0000

Data Index: 399510 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3737. Min Act: -0.0000

Data Index: 461722 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3223. Min Act: -0.0000

Data Index: 923935 (The Pile)

Max Activating Token Index: 233

Text #9

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3935. Min Act: -0.0000

Data Index: 226116 (The Pile)

Max Activating Token Index: 122

Text #10

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3820. Min Act: -0.0000

Data Index: 786579 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1901030 (The Pile)

Max Activating Token Index: 278

Text #12

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3586. Min Act: -0.0000

Data Index: 586398 (The Pile)

Max Activating Token Index: 240

Text #13

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3721. Min Act: -0.0000

Data Index: 118425 (The Pile)

Max Activating Token Index: 368

Text #14

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1415282 (The Pile)

Max Activating Token Index: 261

Text #15

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.4149. Min Act: -0.0000

Data Index: 77471 (The Pile)

Max Activating Token Index: 512

Text #16

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1911931 (The Pile)

Max Activating Token Index: 652

Text #17

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1572915 (The Pile)

Max Activating Token Index: 184

Text #18

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3501. Min Act: -0.0000

Data Index: 899814 (The Pile)

Max Activating Token Index: 338

Text #19

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1112311 (The Pile)

Max Activating Token Index: 365