Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3718 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0405. Min Range: -1.0405

Max Act: 1.0405. Min Act: -0.0000

Data Index: 1276475 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1832926 (The Pile)

Max Activating Token Index: 270

Text #2

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1525745 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1891859 (The Pile)

Max Activating Token Index: 696

Text #4

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1772780 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8273. Min Act: -0.0000

Data Index: 1881415 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.7969. Min Act: -0.0000

Data Index: 276130 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1242397 (The Pile)

Max Activating Token Index: 467

Text #8

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8095. Min Act: -0.0000

Data Index: 697152 (The Pile)

Max Activating Token Index: 232

Text #9

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1820372 (The Pile)

Max Activating Token Index: 559

Text #10

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1159861 (The Pile)

Max Activating Token Index: 597

Text #11

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.6919. Min Act: -0.0000

Data Index: 753667 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.8535. Min Act: -0.0000

Data Index: 887872 (The Pile)

Max Activating Token Index: 558

Text #13

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.7903. Min Act: -0.0000

Data Index: 599501 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.7166. Min Act: -0.0000

Data Index: 302101 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.7117. Min Act: -0.0000

Data Index: 939825 (The Pile)

Max Activating Token Index: 626

Text #16

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.6791. Min Act: -0.0000

Data Index: 10535 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1763681 (The Pile)

Max Activating Token Index: 389

Text #18

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1916693 (The Pile)

Max Activating Token Index: 46

Text #19

Max Range: 1.0405. Min Range: -1.0405

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1299310 (The Pile)

Max Activating Token Index: 332