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

Dataset: The Pile

Neuron 2238 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2302. Min Act: -0.0000

Data Index: 821757 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.3160. Min Act: -0.0000

Data Index: 760408 (The Pile)

Max Activating Token Index: 424

Text #2

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.3179. Min Act: -0.0000

Data Index: 1878680 (The Pile)

Max Activating Token Index: 460

Text #3

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.3815. Min Act: -0.0000

Data Index: 891552 (The Pile)

Max Activating Token Index: 406

Text #4

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1700. Min Act: -0.0000

Data Index: 285847 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2376. Min Act: -0.0000

Data Index: 741907 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2146. Min Act: -0.0000

Data Index: 1864555 (The Pile)

Max Activating Token Index: 474

Text #7

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2385. Min Act: -0.0000

Data Index: 73169 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1252. Min Act: -0.0000

Data Index: 1124217 (The Pile)

Max Activating Token Index: 673

Text #9

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1601. Min Act: -0.0000

Data Index: 1101927 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2190. Min Act: -0.0000

Data Index: 683561 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1203. Min Act: -0.0000

Data Index: 221772 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2462. Min Act: -0.0000

Data Index: 578544 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.2419. Min Act: -0.0000

Data Index: 1891952 (The Pile)

Max Activating Token Index: 661

Text #14

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0374. Min Act: -0.0000

Data Index: 406369 (The Pile)

Max Activating Token Index: 563

Text #15

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1818905 (The Pile)

Max Activating Token Index: 246

Text #16

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1534. Min Act: -0.0000

Data Index: 317816 (The Pile)

Max Activating Token Index: 664

Text #17

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1830. Min Act: -0.0000

Data Index: 1861808 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1710664 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.0950. Min Act: -0.0000

Data Index: 1383480 (The Pile)

Max Activating Token Index: 645