Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1040 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1403783 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1997. Min Act: -0.0000

Data Index: 589102 (The Pile)

Max Activating Token Index: 848

Text #2

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1389499 (The Pile)

Max Activating Token Index: 896

Text #3

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1341491 (The Pile)

Max Activating Token Index: 792

Text #4

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1958327 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1862217 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1890. Min Act: -0.0000

Data Index: 511673 (The Pile)

Max Activating Token Index: 1004

Text #7

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1758467 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1554800 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1858. Min Act: -0.0000

Data Index: 969312 (The Pile)

Max Activating Token Index: 494

Text #10

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1841. Min Act: -0.0000

Data Index: 828769 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1688. Min Act: -0.0001

Data Index: 1835131 (The Pile)

Max Activating Token Index: 937

Text #12

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1765190 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1615. Min Act: -0.0000

Data Index: 385928 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1739843 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1615. Min Act: -0.0000

Data Index: 211724 (The Pile)

Max Activating Token Index: 961

Text #16

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1570457 (The Pile)

Max Activating Token Index: 161

Text #17

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1515. Min Act: -0.0000

Data Index: 774116 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1581. Min Act: -0.0001

Data Index: 1186731 (The Pile)

Max Activating Token Index: 157

Text #19

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1547423 (The Pile)

Max Activating Token Index: 918