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

Dataset: The Pile

Neuron 3620 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: 1.5688. Min Range: -1.5688

Max Act: 1.5688. Min Act: -0.0000

Data Index: 1191282 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4525. Min Act: -0.0000

Data Index: 141022 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4444. Min Act: -0.0000

Data Index: 218846 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4151. Min Act: -0.0000

Data Index: 458817 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4817. Min Act: -0.0000

Data Index: 1071726 (The Pile)

Max Activating Token Index: 253

Text #5

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4614. Min Act: -0.0000

Data Index: 509857 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3566. Min Act: -0.0000

Data Index: 1519388 (The Pile)

Max Activating Token Index: 401

Text #7

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3591. Min Act: -0.0000

Data Index: 1288867 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4285. Min Act: -0.0000

Data Index: 840798 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4887. Min Act: -0.0000

Data Index: 776579 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4166. Min Act: -0.0000

Data Index: 1921098 (The Pile)

Max Activating Token Index: 255

Text #11

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3900. Min Act: -0.0000

Data Index: 1794362 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3097. Min Act: -0.0000

Data Index: 148613 (The Pile)

Max Activating Token Index: 811

Text #13

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.2800. Min Act: -0.0000

Data Index: 152902 (The Pile)

Max Activating Token Index: 413

Text #14

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3621. Min Act: -0.0000

Data Index: 1593194 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3543. Min Act: -0.0000

Data Index: 1566869 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3499. Min Act: -0.0000

Data Index: 663025 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3193. Min Act: -0.0000

Data Index: 1723801 (The Pile)

Max Activating Token Index: 838

Text #18

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3052. Min Act: -0.0000

Data Index: 1971638 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3130. Min Act: -0.0000

Data Index: 1284408 (The Pile)

Max Activating Token Index: 797