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

Dataset: The Pile

Neuron 1630 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7688. Min Act: -0.0000

Data Index: 68346 (The Pile)

Max Activating Token Index: 53

Text #1

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1567050 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6437. Min Act: -0.0000

Data Index: 358425 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6186. Min Act: -0.0000

Data Index: 702053 (The Pile)

Max Activating Token Index: 281

Text #4

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5922. Min Act: -0.0000

Data Index: 21252 (The Pile)

Max Activating Token Index: 612

Text #5

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1957788 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5914. Min Act: 0.0000

Data Index: 479125 (The Pile)

Max Activating Token Index: 221

Text #7

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1750892 (The Pile)

Max Activating Token Index: 860

Text #8

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5715. Min Act: 0.0000

Data Index: 1185055 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5410. Min Act: -0.0000

Data Index: 734456 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5584. Min Act: -0.0000

Data Index: 9623 (The Pile)

Max Activating Token Index: 139

Text #11

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1353554 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1548255 (The Pile)

Max Activating Token Index: 795

Text #13

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1999395 (The Pile)

Max Activating Token Index: 950

Text #14

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1635115 (The Pile)

Max Activating Token Index: 444

Text #15

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.4993. Min Act: -0.0000

Data Index: 269923 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1361521 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5203. Min Act: -0.0000

Data Index: 976253 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.5394. Min Act: -0.0000

Data Index: 643456 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1257443 (The Pile)

Max Activating Token Index: 683