Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3331 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1588530 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.2747. Min Act: -0.0000

Data Index: 357733 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.2319. Min Act: -0.0000

Data Index: 780300 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1648894 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.1229. Min Act: -0.0000

Data Index: 1035016 (The Pile)

Max Activating Token Index: 804

Text #5

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.1455. Min Act: -0.0000

Data Index: 1702756 (The Pile)

Max Activating Token Index: 827

Text #6

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.2052. Min Act: -0.0000

Data Index: 1762507 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.1473. Min Act: -0.0000

Data Index: 881049 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.1224. Min Act: -0.0000

Data Index: 135349 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1315671 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.1565. Min Act: -0.0000

Data Index: 895113 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.1137. Min Act: -0.0000

Data Index: 780255 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.0726. Min Act: -0.0000

Data Index: 1206236 (The Pile)

Max Activating Token Index: 475

Text #13

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.0593. Min Act: -0.0000

Data Index: 438444 (The Pile)

Max Activating Token Index: 815

Text #14

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.0972. Min Act: -0.0000

Data Index: 769849 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.0860. Min Act: -0.0000

Data Index: 1683731 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.0545. Min Act: -0.0000

Data Index: 316786 (The Pile)

Max Activating Token Index: 272

Text #17

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.0914. Min Act: -0.0000

Data Index: 398266 (The Pile)

Max Activating Token Index: 515

Text #18

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.1262. Min Act: -0.0000

Data Index: 1436977 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.0569. Min Act: -0.0000

Data Index: 697462 (The Pile)

Max Activating Token Index: 105