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

Dataset: The Pile

Neuron 2553 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.9234. Min Act: -0.0000

Data Index: 173038 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1967768 (The Pile)

Max Activating Token Index: 497

Text #2

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.8154. Min Act: -0.0000

Data Index: 851073 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1506376 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.7272. Min Act: -0.0000

Data Index: 578859 (The Pile)

Max Activating Token Index: 895

Text #5

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.8374. Min Act: -0.0000

Data Index: 919177 (The Pile)

Max Activating Token Index: 897

Text #6

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.7220. Min Act: -0.0000

Data Index: 548709 (The Pile)

Max Activating Token Index: 1001

Text #7

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.7252. Min Act: -0.0000

Data Index: 509743 (The Pile)

Max Activating Token Index: 1010

Text #8

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.6893. Min Act: -0.0000

Data Index: 409588 (The Pile)

Max Activating Token Index: 401

Text #9

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1572987 (The Pile)

Max Activating Token Index: 886

Text #10

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.7304. Min Act: -0.0000

Data Index: 879425 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.6944. Min Act: -0.0000

Data Index: 326433 (The Pile)

Max Activating Token Index: 656

Text #12

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1473115 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1771040 (The Pile)

Max Activating Token Index: 682

Text #14

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1220457 (The Pile)

Max Activating Token Index: 899

Text #15

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1893339 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1764340 (The Pile)

Max Activating Token Index: 958

Text #17

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1861248 (The Pile)

Max Activating Token Index: 826

Text #18

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.6695. Min Act: -0.0000

Data Index: 29804 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1597840 (The Pile)

Max Activating Token Index: 142