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

Dataset: The Pile

Neuron 3615 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.1733. Min Act: -0.0000

Data Index: 178892 (The Pile)

Max Activating Token Index: 460

Text #1

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.2253. Min Act: -0.0000

Data Index: 1299450 (The Pile)

Max Activating Token Index: 597

Text #2

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1860837 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.1436. Min Act: -0.0000

Data Index: 1021454 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.1244. Min Act: -0.0000

Data Index: 919621 (The Pile)

Max Activating Token Index: 822

Text #5

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0670. Min Act: -0.0000

Data Index: 228800 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0585. Min Act: -0.0000

Data Index: 1084619 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.1899. Min Act: -0.0000

Data Index: 1850965 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0919. Min Act: -0.0000

Data Index: 873579 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1540893 (The Pile)

Max Activating Token Index: 616

Text #10

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0969. Min Act: -0.0000

Data Index: 159715 (The Pile)

Max Activating Token Index: 530

Text #11

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1542535 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0600. Min Act: -0.0000

Data Index: 1112253 (The Pile)

Max Activating Token Index: 83

Text #13

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0350. Min Act: -0.0000

Data Index: 1999324 (The Pile)

Max Activating Token Index: 792

Text #14

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0383. Min Act: -0.0000

Data Index: 1344118 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.1004. Min Act: -0.0000

Data Index: 392976 (The Pile)

Max Activating Token Index: 889

Text #16

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0343. Min Act: -0.0000

Data Index: 972921 (The Pile)

Max Activating Token Index: 303

Text #17

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0206. Min Act: -0.0000

Data Index: 34153 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 1.2253. Min Range: -1.2253

Max Act: 0.9920. Min Act: -0.0000

Data Index: 639018 (The Pile)

Max Activating Token Index: 451

Text #19

Max Range: 1.2253. Min Range: -1.2253

Max Act: 1.0128. Min Act: -0.0000

Data Index: 15299 (The Pile)

Max Activating Token Index: 145