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

Dataset: The Pile

Neuron 3370 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.8760. Min Act: -0.0000

Data Index: 679071 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.8711. Min Act: -0.0000

Data Index: 277555 (The Pile)

Max Activating Token Index: 474

Text #2

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.8822. Min Act: -0.0000

Data Index: 33605 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.8774. Min Act: -0.0000

Data Index: 972231 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.7858. Min Act: -0.0000

Data Index: 1555525 (The Pile)

Max Activating Token Index: 591

Text #5

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.8035. Min Act: -0.0000

Data Index: 161930 (The Pile)

Max Activating Token Index: 474

Text #6

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.7767. Min Act: -0.0000

Data Index: 654695 (The Pile)

Max Activating Token Index: 431

Text #7

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.7726. Min Act: -0.0000

Data Index: 1879692 (The Pile)

Max Activating Token Index: 513

Text #8

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.7323. Min Act: -0.0000

Data Index: 971054 (The Pile)

Max Activating Token Index: 371

Text #9

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.6018. Min Act: -0.0000

Data Index: 1712541 (The Pile)

Max Activating Token Index: 740

Text #10

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.6823. Min Act: -0.0000

Data Index: 275482 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.6763. Min Act: -0.0000

Data Index: 1643985 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.6933. Min Act: -0.0000

Data Index: 1458112 (The Pile)

Max Activating Token Index: 225

Text #13

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.6429. Min Act: -0.0000

Data Index: 583705 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.6215. Min Act: -0.0000

Data Index: 995734 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.6400. Min Act: -0.0000

Data Index: 313325 (The Pile)

Max Activating Token Index: 323

Text #16

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.6435. Min Act: -0.0000

Data Index: 1638247 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.6289. Min Act: -0.0000

Data Index: 1587180 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.6226. Min Act: -0.0000

Data Index: 174364 (The Pile)

Max Activating Token Index: 474

Text #19

Max Range: 1.8822. Min Range: -1.8822

Max Act: 1.5491. Min Act: -0.0000

Data Index: 983544 (The Pile)

Max Activating Token Index: 328