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

Dataset: The Pile

Neuron 3321 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: 0.2838. Min Range: -0.2838

Max Act: 0.2838. Min Act: -0.0000

Data Index: 217581 (The Pile)

Max Activating Token Index: 261

Text #1

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2721. Min Act: -0.0000

Data Index: 406528 (The Pile)

Max Activating Token Index: 403

Text #2

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2454. Min Act: -0.0000

Data Index: 544243 (The Pile)

Max Activating Token Index: 759

Text #3

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2498. Min Act: -0.0000

Data Index: 698344 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1943293 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1055883 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1629517 (The Pile)

Max Activating Token Index: 769

Text #7

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2376. Min Act: -0.0000

Data Index: 944117 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1822274 (The Pile)

Max Activating Token Index: 942

Text #9

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1260643 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2315. Min Act: -0.0000

Data Index: 711973 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1856029 (The Pile)

Max Activating Token Index: 819

Text #12

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1559644 (The Pile)

Max Activating Token Index: 773

Text #13

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1879738 (The Pile)

Max Activating Token Index: 213

Text #14

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1185746 (The Pile)

Max Activating Token Index: 411

Text #15

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1830747 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2149. Min Act: -0.0000

Data Index: 720305 (The Pile)

Max Activating Token Index: 526

Text #17

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1459131 (The Pile)

Max Activating Token Index: 580

Text #18

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1044524 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1453843 (The Pile)

Max Activating Token Index: 533