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

Dataset: The Pile

Neuron 2682 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: 0.7158. Min Range: -0.7158

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1617813 (The Pile)

Max Activating Token Index: 583

Text #1

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.7056. Min Act: -0.0000

Data Index: 775892 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1145461 (The Pile)

Max Activating Token Index: 434

Text #3

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1223096 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6180. Min Act: -0.0000

Data Index: 236432 (The Pile)

Max Activating Token Index: 412

Text #5

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6543. Min Act: -0.0000

Data Index: 35513 (The Pile)

Max Activating Token Index: 868

Text #6

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6384. Min Act: -0.0000

Data Index: 50549 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6131. Min Act: -0.0000

Data Index: 221278 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5837. Min Act: -0.0000

Data Index: 824773 (The Pile)

Max Activating Token Index: 450

Text #9

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1822110 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5843. Min Act: -0.0000

Data Index: 468576 (The Pile)

Max Activating Token Index: 694

Text #11

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1257853 (The Pile)

Max Activating Token Index: 800

Text #12

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5432. Min Act: -0.0000

Data Index: 803642 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5807. Min Act: -0.0000

Data Index: 637584 (The Pile)

Max Activating Token Index: 909

Text #14

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5729. Min Act: -0.0000

Data Index: 673969 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1138925 (The Pile)

Max Activating Token Index: 457

Text #16

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1429176 (The Pile)

Max Activating Token Index: 452

Text #17

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1632255 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5572. Min Act: -0.0000

Data Index: 300894 (The Pile)

Max Activating Token Index: 106

Text #19

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5700. Min Act: -0.0000

Data Index: 589965 (The Pile)

Max Activating Token Index: 263