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

Dataset: The Pile

Neuron 272 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: 3.9115. Min Range: -3.9115

Max Act: 3.9115. Min Act: -0.0000

Data Index: 1540096 (The Pile)

Max Activating Token Index: 939

Text #1

Max Range: 3.9115. Min Range: -3.9115

Max Act: 3.6412. Min Act: -0.0000

Data Index: 1703738 (The Pile)

Max Activating Token Index: 3

Text #2

Max Range: 3.9115. Min Range: -3.9115

Max Act: 3.5474. Min Act: -0.0000

Data Index: 1148405 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 3.9115. Min Range: -3.9115

Max Act: 3.3559. Min Act: -0.0000

Data Index: 1122678 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 3.9115. Min Range: -3.9115

Max Act: 3.2955. Min Act: -0.0000

Data Index: 1720673 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 3.9115. Min Range: -3.9115

Max Act: 3.0336. Min Act: -0.0000

Data Index: 1173750 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 3.9115. Min Range: -3.9115

Max Act: 2.8985. Min Act: -0.0000

Data Index: 1391137 (The Pile)

Max Activating Token Index: 593

Text #7

Max Range: 3.9115. Min Range: -3.9115

Max Act: 2.9880. Min Act: -0.0000

Data Index: 399131 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 3.9115. Min Range: -3.9115

Max Act: 2.9026. Min Act: -0.0000

Data Index: 943730 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 3.9115. Min Range: -3.9115

Max Act: 3.0307. Min Act: -0.0000

Data Index: 1157236 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 3.9115. Min Range: -3.9115

Max Act: 2.8222. Min Act: -0.0000

Data Index: 1249131 (The Pile)

Max Activating Token Index: 3

Text #11

Max Range: 3.9115. Min Range: -3.9115

Max Act: 2.7844. Min Act: -0.0000

Data Index: 1848627 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 3.9115. Min Range: -3.9115

Max Act: 2.8427. Min Act: -0.0000

Data Index: 262030 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 3.9115. Min Range: -3.9115

Max Act: 2.5696. Min Act: -0.0000

Data Index: 1113919 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 3.9115. Min Range: -3.9115

Max Act: 2.5819. Min Act: -0.0000

Data Index: 1551678 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 3.9115. Min Range: -3.9115

Max Act: 2.5677. Min Act: -0.0000

Data Index: 32060 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 3.9115. Min Range: -3.9115

Max Act: 2.4545. Min Act: -0.0000

Data Index: 835008 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 3.9115. Min Range: -3.9115

Max Act: 2.5556. Min Act: -0.0000

Data Index: 1760070 (The Pile)

Max Activating Token Index: 285

Text #18

Max Range: 3.9115. Min Range: -3.9115

Max Act: 2.3758. Min Act: -0.0000

Data Index: 252783 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 3.9115. Min Range: -3.9115

Max Act: 2.4645. Min Act: -0.0000

Data Index: 582083 (The Pile)

Max Activating Token Index: 40