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

Dataset: The Pile

Neuron 2282 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: 1.0947. Min Range: -1.0947

Max Act: 1.0947. Min Act: -0.0000

Data Index: 1915509 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1677914 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9697. Min Act: -0.0000

Data Index: 98251 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1784287 (The Pile)

Max Activating Token Index: 601

Text #4

Max Range: 1.0947. Min Range: -1.0947

Max Act: 1.0133. Min Act: -0.0000

Data Index: 467181 (The Pile)

Max Activating Token Index: 801

Text #5

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9490. Min Act: -0.0000

Data Index: 60820 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1589211 (The Pile)

Max Activating Token Index: 885

Text #7

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9130. Min Act: -0.0000

Data Index: 832343 (The Pile)

Max Activating Token Index: 837

Text #8

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1073937 (The Pile)

Max Activating Token Index: 632

Text #9

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8228. Min Act: -0.0000

Data Index: 1764650 (The Pile)

Max Activating Token Index: 256

Text #10

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1676038 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1566325 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1091067 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1446058 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9053. Min Act: -0.0000

Data Index: 290246 (The Pile)

Max Activating Token Index: 955

Text #15

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1757571 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.7708. Min Act: -0.0000

Data Index: 274586 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8116. Min Act: -0.0000

Data Index: 277676 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8072. Min Act: -0.0000

Data Index: 995020 (The Pile)

Max Activating Token Index: 569

Text #19

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.8607. Min Act: -0.0000

Data Index: 251475 (The Pile)

Max Activating Token Index: 863