Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2566 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7712. Min Act: -0.0000

Data Index: 1587184 (The Pile)

Max Activating Token Index: 337

Text #1

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.7166. Min Act: -0.0000

Data Index: 1125071 (The Pile)

Max Activating Token Index: 4

Text #2

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1599095 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5468. Min Act: -0.0000

Data Index: 600853 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5809. Min Act: -0.0000

Data Index: 648313 (The Pile)

Max Activating Token Index: 860

Text #5

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5529. Min Act: -0.0000

Data Index: 179449 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1634209 (The Pile)

Max Activating Token Index: 406

Text #7

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5417. Min Act: -0.0000

Data Index: 503271 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1272851 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5496. Min Act: -0.0000

Data Index: 552973 (The Pile)

Max Activating Token Index: 455

Text #10

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5449. Min Act: -0.0000

Data Index: 589060 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5188. Min Act: -0.0000

Data Index: 949139 (The Pile)

Max Activating Token Index: 339

Text #12

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1676790 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5257. Min Act: -0.0000

Data Index: 568383 (The Pile)

Max Activating Token Index: 402

Text #14

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.4863. Min Act: -0.0000

Data Index: 754593 (The Pile)

Max Activating Token Index: 217

Text #15

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1285851 (The Pile)

Max Activating Token Index: 978

Text #16

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.4947. Min Act: -0.0000

Data Index: 53342 (The Pile)

Max Activating Token Index: 79

Text #17

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.5089. Min Act: -0.0000

Data Index: 221748 (The Pile)

Max Activating Token Index: 693

Text #18

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1615052 (The Pile)

Max Activating Token Index: 224

Text #19

Max Range: 0.7712. Min Range: -0.7712

Max Act: 0.4885. Min Act: -0.0000

Data Index: 642602 (The Pile)

Max Activating Token Index: 780