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

Dataset: The Pile

Neuron 2589 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5344. Min Act: -0.0000

Data Index: 921205 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5445. Min Act: -0.0000

Data Index: 879747 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1592434 (The Pile)

Max Activating Token Index: 565

Text #3

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4950. Min Act: -0.0000

Data Index: 514864 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1163949 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4650. Min Act: -0.0000

Data Index: 742050 (The Pile)

Max Activating Token Index: 807

Text #6

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1519997 (The Pile)

Max Activating Token Index: 676

Text #7

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4147. Min Act: -0.0000

Data Index: 216072 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1766745 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1515465 (The Pile)

Max Activating Token Index: 770

Text #10

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1038088 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1148700 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4338. Min Act: -0.0000

Data Index: 682514 (The Pile)

Max Activating Token Index: 445

Text #13

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1803371 (The Pile)

Max Activating Token Index: 637

Text #14

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1948449 (The Pile)

Max Activating Token Index: 494

Text #15

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1457748 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1908551 (The Pile)

Max Activating Token Index: 636

Text #17

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3974. Min Act: -0.0000

Data Index: 862001 (The Pile)

Max Activating Token Index: 863

Text #18

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4094. Min Act: -0.0000

Data Index: 1193327 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1484232 (The Pile)

Max Activating Token Index: 976