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

Dataset: The Pile

Neuron 806 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: 0.9105. Min Range: -0.9105

Max Act: 0.9105. Min Act: -0.0000

Data Index: 873789 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1864233 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1990476 (The Pile)

Max Activating Token Index: 327

Text #3

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.6522. Min Act: -0.0000

Data Index: 1675361 (The Pile)

Max Activating Token Index: 780

Text #4

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1980096 (The Pile)

Max Activating Token Index: 902

Text #5

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1771823 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.6301. Min Act: -0.0000

Data Index: 318415 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1256656 (The Pile)

Max Activating Token Index: 228

Text #8

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.5755. Min Act: -0.0000

Data Index: 912331 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.6285. Min Act: -0.0000

Data Index: 513386 (The Pile)

Max Activating Token Index: 866

Text #10

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1255584 (The Pile)

Max Activating Token Index: 246

Text #11

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1612486 (The Pile)

Max Activating Token Index: 808

Text #12

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1633979 (The Pile)

Max Activating Token Index: 570

Text #13

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1823005 (The Pile)

Max Activating Token Index: 510

Text #14

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1042285 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1391665 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.5716. Min Act: -0.0000

Data Index: 48163 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.5351. Min Act: -0.0000

Data Index: 212344 (The Pile)

Max Activating Token Index: 262

Text #18

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.5817. Min Act: -0.0000

Data Index: 781389 (The Pile)

Max Activating Token Index: 456

Text #19

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.5940. Min Act: -0.0000

Data Index: 361902 (The Pile)

Max Activating Token Index: 584