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

Dataset: The Pile

Neuron 1203 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1123639 (The Pile)

Max Activating Token Index: 905

Text #1

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0865. Min Act: -0.0000

Data Index: 1288085 (The Pile)

Max Activating Token Index: 849

Text #2

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9507. Min Act: -0.0000

Data Index: 497987 (The Pile)

Max Activating Token Index: 241

Text #3

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8880. Min Act: -0.0000

Data Index: 114267 (The Pile)

Max Activating Token Index: 490

Text #4

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9103. Min Act: -0.0000

Data Index: 813632 (The Pile)

Max Activating Token Index: 376

Text #5

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9454. Min Act: -0.0000

Data Index: 348461 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9050. Min Act: -0.0000

Data Index: 1974516 (The Pile)

Max Activating Token Index: 625

Text #7

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1331437 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1722902 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8507. Min Act: -0.0000

Data Index: 982744 (The Pile)

Max Activating Token Index: 924

Text #10

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1525767 (The Pile)

Max Activating Token Index: 970

Text #11

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8214. Min Act: -0.0000

Data Index: 239772 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.7726. Min Act: -0.0000

Data Index: 1072704 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1635718 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1830590 (The Pile)

Max Activating Token Index: 345

Text #15

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1206076 (The Pile)

Max Activating Token Index: 751

Text #16

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.7689. Min Act: -0.0000

Data Index: 221276 (The Pile)

Max Activating Token Index: 467

Text #17

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1569895 (The Pile)

Max Activating Token Index: 580

Text #18

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.7360. Min Act: -0.0000

Data Index: 315488 (The Pile)

Max Activating Token Index: 747

Text #19

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.7810. Min Act: -0.0000

Data Index: 437586 (The Pile)

Max Activating Token Index: 865