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

Dataset: The Pile

Neuron 2294 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: 0.8879. Min Range: -0.8879

Max Act: 0.8879. Min Act: -0.0000

Data Index: 589680 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.8343. Min Act: -0.0000

Data Index: 959846 (The Pile)

Max Activating Token Index: 405

Text #2

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.7124. Min Act: -0.0000

Data Index: 865555 (The Pile)

Max Activating Token Index: 377

Text #3

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.7097. Min Act: -0.0000

Data Index: 687571 (The Pile)

Max Activating Token Index: 281

Text #4

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1135598 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6545. Min Act: -0.0000

Data Index: 247260 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1061321 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1407856 (The Pile)

Max Activating Token Index: 537

Text #8

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1128133 (The Pile)

Max Activating Token Index: 313

Text #9

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1469025 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.5408. Min Act: -0.0000

Data Index: 609631 (The Pile)

Max Activating Token Index: 206

Text #11

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6181. Min Act: -0.0000

Data Index: 871591 (The Pile)

Max Activating Token Index: 155

Text #12

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.5681. Min Act: -0.0000

Data Index: 13749 (The Pile)

Max Activating Token Index: 228

Text #13

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.5557. Min Act: -0.0000

Data Index: 875272 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.5914. Min Act: -0.0000

Data Index: 940754 (The Pile)

Max Activating Token Index: 790

Text #15

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1870703 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.5445. Min Act: -0.0000

Data Index: 426105 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.5804. Min Act: -0.0000

Data Index: 290003 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1140140 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.5205. Min Act: -0.0000

Data Index: 810122 (The Pile)

Max Activating Token Index: 875