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

Dataset: The Pile

Neuron 3794 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: 0.8777. Min Range: -0.8777

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1204816 (The Pile)

Max Activating Token Index: 421

Text #1

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.8154. Min Act: -0.0000

Data Index: 888605 (The Pile)

Max Activating Token Index: 953

Text #2

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.8189. Min Act: -0.0000

Data Index: 517913 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1955607 (The Pile)

Max Activating Token Index: 499

Text #4

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1090380 (The Pile)

Max Activating Token Index: 844

Text #5

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.8025. Min Act: -0.0000

Data Index: 731595 (The Pile)

Max Activating Token Index: 933

Text #6

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.7756. Min Act: -0.0000

Data Index: 625298 (The Pile)

Max Activating Token Index: 532

Text #7

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1024218 (The Pile)

Max Activating Token Index: 467

Text #8

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1336665 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1171877 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.7278. Min Act: -0.0000

Data Index: 491296 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.7296. Min Act: -0.0000

Data Index: 655852 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.7303. Min Act: -0.0000

Data Index: 809571 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1333359 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6771. Min Act: -0.0000

Data Index: 262835 (The Pile)

Max Activating Token Index: 474

Text #15

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6888. Min Act: -0.0000

Data Index: 335939 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1955321 (The Pile)

Max Activating Token Index: 272

Text #17

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1881378 (The Pile)

Max Activating Token Index: 690

Text #18

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.7003. Min Act: -0.0000

Data Index: 146266 (The Pile)

Max Activating Token Index: 960

Text #19

Max Range: 0.8777. Min Range: -0.8777

Max Act: 0.6983. Min Act: -0.0000

Data Index: 940132 (The Pile)

Max Activating Token Index: 485