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

Dataset: The Pile

Neuron 1836 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: 0.8021. Min Range: -0.8021

Max Act: 0.8021. Min Act: -0.0000

Data Index: 981075 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.6488. Min Act: -0.0000

Data Index: 478795 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1977412 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.7091. Min Act: -0.0000

Data Index: 703947 (The Pile)

Max Activating Token Index: 340

Text #4

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1608244 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1021802 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1694160 (The Pile)

Max Activating Token Index: 482

Text #7

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.7046. Min Act: -0.0000

Data Index: 250488 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.6102. Min Act: -0.0000

Data Index: 551346 (The Pile)

Max Activating Token Index: 518

Text #9

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.6095. Min Act: -0.0000

Data Index: 781180 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1514869 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.6516. Min Act: -0.0000

Data Index: 402070 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.6233. Min Act: -0.0000

Data Index: 179229 (The Pile)

Max Activating Token Index: 465

Text #13

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1575453 (The Pile)

Max Activating Token Index: 987

Text #14

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.6504. Min Act: -0.0000

Data Index: 558497 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1846394 (The Pile)

Max Activating Token Index: 550

Text #16

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.6143. Min Act: -0.0000

Data Index: 574671 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1825787 (The Pile)

Max Activating Token Index: 291

Text #18

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.6041. Min Act: -0.0000

Data Index: 993061 (The Pile)

Max Activating Token Index: 80

Text #19

Max Range: 0.8021. Min Range: -0.8021

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1040714 (The Pile)

Max Activating Token Index: 395