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

Dataset: The Pile

Neuron 4429 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: 0.7988. Min Range: -0.7988

Max Act: 0.7988. Min Act: -0.0000

Data Index: 784713 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1606413 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1772923 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5838. Min Act: 0.0000

Data Index: 300334 (The Pile)

Max Activating Token Index: 539

Text #4

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1185137 (The Pile)

Max Activating Token Index: 150

Text #5

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1296421 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5589. Min Act: 0.0000

Data Index: 1202364 (The Pile)

Max Activating Token Index: 994

Text #7

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5264. Min Act: 0.0000

Data Index: 853143 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1508159 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5720. Min Act: 0.0000

Data Index: 188142 (The Pile)

Max Activating Token Index: 369

Text #10

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5548. Min Act: 0.0000

Data Index: 707439 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5696. Min Act: -0.0000

Data Index: 623138 (The Pile)

Max Activating Token Index: 589

Text #12

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5701. Min Act: -0.0000

Data Index: 468712 (The Pile)

Max Activating Token Index: 675

Text #13

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1976263 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1935747 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5139. Min Act: 0.0000

Data Index: 772421 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1693168 (The Pile)

Max Activating Token Index: 653

Text #17

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1990591 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1299115 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4893. Min Act: -0.0000

Data Index: 311875 (The Pile)

Max Activating Token Index: 928