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

Dataset: The Pile

Neuron 177 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: 0.8819. Min Range: -0.8819

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1368580 (The Pile)

Max Activating Token Index: 544

Text #1

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8819. Min Act: -0.0000

Data Index: 519179 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8172. Min Act: -0.0000

Data Index: 969751 (The Pile)

Max Activating Token Index: 755

Text #3

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7579. Min Act: -0.0000

Data Index: 220171 (The Pile)

Max Activating Token Index: 737

Text #4

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1844104 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7903. Min Act: -0.0000

Data Index: 961328 (The Pile)

Max Activating Token Index: 253

Text #6

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1298369 (The Pile)

Max Activating Token Index: 834

Text #7

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1951275 (The Pile)

Max Activating Token Index: 202

Text #8

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8066. Min Act: -0.0000

Data Index: 192327 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7719. Min Act: -0.0000

Data Index: 970682 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8035. Min Act: -0.0000

Data Index: 375227 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7512. Min Act: -0.0000

Data Index: 625480 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8156. Min Act: -0.0000

Data Index: 735163 (The Pile)

Max Activating Token Index: 589

Text #13

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1629952 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7943. Min Act: -0.0000

Data Index: 993197 (The Pile)

Max Activating Token Index: 757

Text #15

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8201. Min Act: -0.0000

Data Index: 621319 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7900. Min Act: -0.0000

Data Index: 108425 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1009212 (The Pile)

Max Activating Token Index: 789

Text #18

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8046. Min Act: -0.0000

Data Index: 588322 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8243. Min Act: -0.0000

Data Index: 322498 (The Pile)

Max Activating Token Index: 142