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

Dataset: The Pile

Neuron 2845 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: 0.7194. Min Range: -0.7194

Max Act: 0.7194. Min Act: -0.0000

Data Index: 362508 (The Pile)

Max Activating Token Index: 803

Text #1

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6780. Min Act: -0.0000

Data Index: 911121 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6287. Min Act: -0.0000

Data Index: 38418 (The Pile)

Max Activating Token Index: 468

Text #3

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1892439 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6090. Min Act: -0.0000

Data Index: 454146 (The Pile)

Max Activating Token Index: 486

Text #5

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1433251 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6102. Min Act: -0.0000

Data Index: 650964 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1136230 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1784842 (The Pile)

Max Activating Token Index: 928

Text #9

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1986595 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6030. Min Act: -0.0000

Data Index: 9586 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6174. Min Act: -0.0000

Data Index: 790608 (The Pile)

Max Activating Token Index: 887

Text #12

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5956. Min Act: -0.0000

Data Index: 157422 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1450217 (The Pile)

Max Activating Token Index: 983

Text #14

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5889. Min Act: -0.0000

Data Index: 368899 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1315872 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.6034. Min Act: -0.0000

Data Index: 612564 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1545528 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5969. Min Act: -0.0000

Data Index: 713639 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1622380 (The Pile)

Max Activating Token Index: 793