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

Dataset: The Pile

Neuron 30 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: 0.8999. Min Range: -0.8999

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1198943 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.8132. Min Act: -0.0000

Data Index: 392375 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1973199 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.7504. Min Act: -0.0000

Data Index: 14381 (The Pile)

Max Activating Token Index: 160

Text #4

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1865924 (The Pile)

Max Activating Token Index: 698

Text #5

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1780686 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.6452. Min Act: -0.0000

Data Index: 273552 (The Pile)

Max Activating Token Index: 313

Text #7

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1672856 (The Pile)

Max Activating Token Index: 182

Text #8

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.6392. Min Act: -0.0000

Data Index: 492454 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1032404 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1243506 (The Pile)

Max Activating Token Index: 604

Text #11

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.6162. Min Act: -0.0000

Data Index: 282644 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1419914 (The Pile)

Max Activating Token Index: 719

Text #13

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1455203 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1846996 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.5900. Min Act: -0.0000

Data Index: 587497 (The Pile)

Max Activating Token Index: 478

Text #16

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1017007 (The Pile)

Max Activating Token Index: 305

Text #17

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.5771. Min Act: -0.0000

Data Index: 512945 (The Pile)

Max Activating Token Index: 482

Text #18

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.6299. Min Act: -0.0000

Data Index: 904074 (The Pile)

Max Activating Token Index: 668

Text #19

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.5557. Min Act: -0.0000

Data Index: 76295 (The Pile)

Max Activating Token Index: 242