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

Dataset: The Pile

Neuron 3449 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.7015. Min Act: 0.0000

Data Index: 1575320 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1320859 (The Pile)

Max Activating Token Index: 402

Text #2

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5227. Min Act: -0.0000

Data Index: 573457 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5239. Min Act: -0.0000

Data Index: 43218 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1216498 (The Pile)

Max Activating Token Index: 594

Text #5

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4896. Min Act: -0.0000

Data Index: 1755811 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4798. Min Act: -0.0000

Data Index: 1998807 (The Pile)

Max Activating Token Index: 656

Text #7

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1066622 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4623. Min Act: -0.0000

Data Index: 599716 (The Pile)

Max Activating Token Index: 334

Text #9

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1325455 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1688959 (The Pile)

Max Activating Token Index: 112

Text #11

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4621. Min Act: -0.0000

Data Index: 565927 (The Pile)

Max Activating Token Index: 578

Text #12

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1114465 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4399. Min Act: -0.0000

Data Index: 1949344 (The Pile)

Max Activating Token Index: 881

Text #14

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4393. Min Act: -0.0000

Data Index: 505005 (The Pile)

Max Activating Token Index: 421

Text #15

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4249. Min Act: -0.0000

Data Index: 644851 (The Pile)

Max Activating Token Index: 698

Text #16

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4400. Min Act: -0.0000

Data Index: 323826 (The Pile)

Max Activating Token Index: 848

Text #17

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1866548 (The Pile)

Max Activating Token Index: 139

Text #18

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4628. Min Act: -0.0000

Data Index: 914422 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1291319 (The Pile)

Max Activating Token Index: 260