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

Dataset: The Pile

Neuron 1631 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1446580 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1474666 (The Pile)

Max Activating Token Index: 722

Text #2

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.8332. Min Act: -0.0000

Data Index: 355046 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6710. Min Act: -0.0000

Data Index: 98539 (The Pile)

Max Activating Token Index: 666

Text #4

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1599545 (The Pile)

Max Activating Token Index: 791

Text #5

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1167743 (The Pile)

Max Activating Token Index: 839

Text #6

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1616626 (The Pile)

Max Activating Token Index: 917

Text #7

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.7545. Min Act: -0.0000

Data Index: 602234 (The Pile)

Max Activating Token Index: 836

Text #8

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6974. Min Act: -0.0000

Data Index: 996180 (The Pile)

Max Activating Token Index: 197

Text #9

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1874681 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1168760 (The Pile)

Max Activating Token Index: 366

Text #11

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6452. Min Act: -0.0000

Data Index: 189022 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6467. Min Act: -0.0000

Data Index: 344420 (The Pile)

Max Activating Token Index: 358

Text #13

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1628244 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6174. Min Act: -0.0000

Data Index: 577140 (The Pile)

Max Activating Token Index: 1005

Text #15

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1870284 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6302. Min Act: -0.0000

Data Index: 923889 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1270478 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1159420 (The Pile)

Max Activating Token Index: 703

Text #19

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5846. Min Act: -0.0000

Data Index: 452302 (The Pile)

Max Activating Token Index: 5