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

Dataset: The Pile

Neuron 693 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: 5.2064. Min Range: -5.2064

Max Act: 5.2064. Min Act: -0.0000

Data Index: 25924 (The Pile)

Max Activating Token Index: 510

Text #1

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.5575. Min Act: -0.0000

Data Index: 199287 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.3491. Min Act: -0.0000

Data Index: 500431 (The Pile)

Max Activating Token Index: 813

Text #3

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.3978. Min Act: -0.0000

Data Index: 1036221 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.5583. Min Act: -0.0000

Data Index: 1839737 (The Pile)

Max Activating Token Index: 319

Text #5

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.6925. Min Act: -0.0000

Data Index: 589473 (The Pile)

Max Activating Token Index: 1019

Text #6

Max Range: 5.2064. Min Range: -5.2064

Max Act: 3.9756. Min Act: -0.0000

Data Index: 1592363 (The Pile)

Max Activating Token Index: 707

Text #7

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.6361. Min Act: -0.0000

Data Index: 588097 (The Pile)

Max Activating Token Index: 757

Text #8

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.5561. Min Act: -0.0000

Data Index: 1706759 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 5.2064. Min Range: -5.2064

Max Act: 3.8342. Min Act: -0.0000

Data Index: 590760 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.1748. Min Act: -0.0000

Data Index: 459131 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.1719. Min Act: -0.0000

Data Index: 62468 (The Pile)

Max Activating Token Index: 421

Text #12

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.1641. Min Act: -0.0000

Data Index: 1492784 (The Pile)

Max Activating Token Index: 742

Text #13

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.5110. Min Act: -0.0000

Data Index: 678393 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.3217. Min Act: -0.0000

Data Index: 472730 (The Pile)

Max Activating Token Index: 525

Text #15

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.2961. Min Act: -0.0000

Data Index: 1821251 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.2946. Min Act: -0.0000

Data Index: 826082 (The Pile)

Max Activating Token Index: 959

Text #17

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.4611. Min Act: -0.0000

Data Index: 312328 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.2771. Min Act: -0.0000

Data Index: 586977 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 5.2064. Min Range: -5.2064

Max Act: 4.2561. Min Act: -0.0000

Data Index: 84475 (The Pile)

Max Activating Token Index: 152