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

Dataset: The Pile

Neuron 213 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.9244. Min Act: -0.0000

Data Index: 118264 (The Pile)

Max Activating Token Index: 872

Text #1

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1848978 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.6965. Min Act: -0.0000

Data Index: 123535 (The Pile)

Max Activating Token Index: 858

Text #3

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.7122. Min Act: -0.0000

Data Index: 198513 (The Pile)

Max Activating Token Index: 790

Text #4

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.6644. Min Act: -0.0000

Data Index: 626883 (The Pile)

Max Activating Token Index: 407

Text #5

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.6889. Min Act: -0.0000

Data Index: 733799 (The Pile)

Max Activating Token Index: 720

Text #6

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1027392 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1720854 (The Pile)

Max Activating Token Index: 729

Text #8

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.7091. Min Act: -0.0000

Data Index: 595067 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.6388. Min Act: -0.0000

Data Index: 75838 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1674898 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.6527. Min Act: -0.0000

Data Index: 612817 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.6425. Min Act: -0.0000

Data Index: 630238 (The Pile)

Max Activating Token Index: 860

Text #13

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1179268 (The Pile)

Max Activating Token Index: 92

Text #14

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.6196. Min Act: -0.0000

Data Index: 324592 (The Pile)

Max Activating Token Index: 339

Text #15

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.5861. Min Act: -0.0000

Data Index: 889605 (The Pile)

Max Activating Token Index: 806

Text #16

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1511239 (The Pile)

Max Activating Token Index: 832

Text #17

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1440522 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1892448 (The Pile)

Max Activating Token Index: 199

Text #19

Max Range: 0.9244. Min Range: -0.9244

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1219959 (The Pile)

Max Activating Token Index: 581