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

Dataset: The Pile

Neuron 3936 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 10.4388. Min Range: -10.4388

Max Act: 10.4388. Min Act: -0.0000

Data Index: 1081545 (The Pile)

Max Activating Token Index: 790

Text #1

Max Range: 10.4388. Min Range: -10.4388

Max Act: 10.2880. Min Act: -0.0000

Data Index: 1887677 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 10.4388. Min Range: -10.4388

Max Act: 9.6668. Min Act: -0.0000

Data Index: 279623 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 10.4388. Min Range: -10.4388

Max Act: 9.2683. Min Act: -0.0000

Data Index: 772846 (The Pile)

Max Activating Token Index: 409

Text #4

Max Range: 10.4388. Min Range: -10.4388

Max Act: 8.6903. Min Act: -0.0000

Data Index: 523584 (The Pile)

Max Activating Token Index: 381

Text #5

Max Range: 10.4388. Min Range: -10.4388

Max Act: 8.4807. Min Act: -0.0000

Data Index: 1097822 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 10.4388. Min Range: -10.4388

Max Act: 8.2721. Min Act: -0.0000

Data Index: 1534420 (The Pile)

Max Activating Token Index: 369

Text #7

Max Range: 10.4388. Min Range: -10.4388

Max Act: 7.6814. Min Act: -0.0000

Data Index: 1412522 (The Pile)

Max Activating Token Index: 503

Text #8

Max Range: 10.4388. Min Range: -10.4388

Max Act: 7.6293. Min Act: -0.0000

Data Index: 654227 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 10.4388. Min Range: -10.4388

Max Act: 7.8684. Min Act: -0.0000

Data Index: 1347170 (The Pile)

Max Activating Token Index: 647

Text #10

Max Range: 10.4388. Min Range: -10.4388

Max Act: 7.1354. Min Act: -0.0000

Data Index: 979513 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 10.4388. Min Range: -10.4388

Max Act: 7.8169. Min Act: -0.0000

Data Index: 168205 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 10.4388. Min Range: -10.4388

Max Act: 7.2132. Min Act: -0.0000

Data Index: 459704 (The Pile)

Max Activating Token Index: 555

Text #13

Max Range: 10.4388. Min Range: -10.4388

Max Act: 6.8195. Min Act: -0.0000

Data Index: 1668525 (The Pile)

Max Activating Token Index: 447

Text #14

Max Range: 10.4388. Min Range: -10.4388

Max Act: 7.3643. Min Act: -0.0000

Data Index: 1156873 (The Pile)

Max Activating Token Index: 84

Text #15

Max Range: 10.4388. Min Range: -10.4388

Max Act: 7.7547. Min Act: -0.0000

Data Index: 1960819 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 10.4388. Min Range: -10.4388

Max Act: 7.4921. Min Act: -0.0000

Data Index: 664121 (The Pile)

Max Activating Token Index: 517

Text #17

Max Range: 10.4388. Min Range: -10.4388

Max Act: 7.2776. Min Act: -0.0000

Data Index: 824456 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 10.4388. Min Range: -10.4388

Max Act: 7.0337. Min Act: -0.0000

Data Index: 1679332 (The Pile)

Max Activating Token Index: 641

Text #19

Max Range: 10.4388. Min Range: -10.4388

Max Act: 7.2082. Min Act: -0.0000

Data Index: 1515581 (The Pile)

Max Activating Token Index: 872