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

Dataset: The Pile

Neuron 249 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.6831. Min Act: -0.0000

Data Index: 1904605 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.6526. Min Act: -0.0000

Data Index: 1122605 (The Pile)

Max Activating Token Index: 418

Text #2

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.6499. Min Act: -0.0000

Data Index: 1717852 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.5622. Min Act: -0.0000

Data Index: 330553 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4935. Min Act: -0.0000

Data Index: 886025 (The Pile)

Max Activating Token Index: 230

Text #5

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4470. Min Act: -0.0000

Data Index: 1858660 (The Pile)

Max Activating Token Index: 775

Text #6

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4724. Min Act: -0.0000

Data Index: 1972441 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4815. Min Act: -0.0000

Data Index: 1727609 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4645. Min Act: -0.0000

Data Index: 1735940 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4786. Min Act: -0.0000

Data Index: 1467787 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4077. Min Act: -0.0000

Data Index: 1463870 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.4054. Min Act: -0.0000

Data Index: 1884849 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.3644. Min Act: -0.0000

Data Index: 40268 (The Pile)

Max Activating Token Index: 277

Text #13

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.3485. Min Act: -0.0000

Data Index: 1546858 (The Pile)

Max Activating Token Index: 929

Text #14

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.3204. Min Act: -0.0000

Data Index: 1884162 (The Pile)

Max Activating Token Index: 247

Text #15

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.3409. Min Act: -0.0000

Data Index: 1689039 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.3993. Min Act: -0.0000

Data Index: 1832175 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.3101. Min Act: -0.0000

Data Index: 1759783 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.3348. Min Act: -0.0000

Data Index: 857877 (The Pile)

Max Activating Token Index: 852

Text #19

Max Range: 1.6831. Min Range: -1.6831

Max Act: 1.3158. Min Act: -0.0000

Data Index: 642589 (The Pile)

Max Activating Token Index: 1021