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

Dataset: The Pile

Neuron 4507 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: 1.2030. Min Range: -1.2030

Max Act: 1.2030. Min Act: -0.0000

Data Index: 1602062 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 1.2030. Min Range: -1.2030

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1182953 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 1.2030. Min Range: -1.2030

Max Act: 1.1012. Min Act: -0.0000

Data Index: 1892881 (The Pile)

Max Activating Token Index: 997

Text #3

Max Range: 1.2030. Min Range: -1.2030

Max Act: 1.1453. Min Act: -0.0000

Data Index: 200787 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 1.2030. Min Range: -1.2030

Max Act: 1.0282. Min Act: -0.0000

Data Index: 627707 (The Pile)

Max Activating Token Index: 251

Text #5

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.9137. Min Act: -0.0000

Data Index: 89280 (The Pile)

Max Activating Token Index: 564

Text #6

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.9593. Min Act: -0.0000

Data Index: 1892662 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.9455. Min Act: -0.0000

Data Index: 1669893 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.9373. Min Act: -0.0000

Data Index: 3841 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.9281. Min Act: -0.0000

Data Index: 872301 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1916371 (The Pile)

Max Activating Token Index: 966

Text #11

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.8472. Min Act: -0.0000

Data Index: 211221 (The Pile)

Max Activating Token Index: 619

Text #12

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.8945. Min Act: -0.0000

Data Index: 542706 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.9244. Min Act: -0.0000

Data Index: 823826 (The Pile)

Max Activating Token Index: 1019

Text #14

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.8130. Min Act: -0.0000

Data Index: 981231 (The Pile)

Max Activating Token Index: 1006

Text #15

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.8072. Min Act: -0.0000

Data Index: 1974011 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.8425. Min Act: 0.0000

Data Index: 68807 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.8955. Min Act: -0.0000

Data Index: 1401930 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1317369 (The Pile)

Max Activating Token Index: 229

Text #19

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1474773 (The Pile)

Max Activating Token Index: 906