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

Dataset: The Pile

Neuron 4232 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4086. Min Range: -3.4086

Max Act: 3.3753. Min Act: -0.0000

Data Index: 916037 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 3.4086. Min Range: -3.4086

Max Act: 3.4086. Min Act: -0.0000

Data Index: 1940917 (The Pile)

Max Activating Token Index: 889

Text #2

Max Range: 3.4086. Min Range: -3.4086

Max Act: 3.1000. Min Act: -0.0000

Data Index: 608008 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 3.4086. Min Range: -3.4086

Max Act: 3.0182. Min Act: -0.0000

Data Index: 294735 (The Pile)

Max Activating Token Index: 270

Text #4

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.8846. Min Act: 0.0000

Data Index: 1883336 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.9809. Min Act: -0.0000

Data Index: 856584 (The Pile)

Max Activating Token Index: 281

Text #6

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.6739. Min Act: -0.0000

Data Index: 1059321 (The Pile)

Max Activating Token Index: 781

Text #7

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.8891. Min Act: -0.0000

Data Index: 1740623 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 3.4086. Min Range: -3.4086

Max Act: 3.1550. Min Act: -0.0000

Data Index: 420698 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.9968. Min Act: -0.0000

Data Index: 352266 (The Pile)

Max Activating Token Index: 669

Text #10

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.8400. Min Act: -0.0000

Data Index: 945419 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.9842. Min Act: -0.0000

Data Index: 1727718 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.9396. Min Act: -0.0000

Data Index: 558575 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.2512. Min Act: -0.0000

Data Index: 1230777 (The Pile)

Max Activating Token Index: 808

Text #14

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.6264. Min Act: -0.0000

Data Index: 63114 (The Pile)

Max Activating Token Index: 798

Text #15

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.6597. Min Act: 0.0000

Data Index: 533451 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.6211. Min Act: -0.0000

Data Index: 847336 (The Pile)

Max Activating Token Index: 319

Text #17

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.7460. Min Act: -0.0000

Data Index: 1357463 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.6384. Min Act: -0.0000

Data Index: 1510596 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 3.4086. Min Range: -3.4086

Max Act: 2.5272. Min Act: -0.0000

Data Index: 247787 (The Pile)

Max Activating Token Index: 221