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

Dataset: The Pile

Neuron 590 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.5680. Min Act: -0.0000

Data Index: 1712437 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.3885. Min Act: -0.0000

Data Index: 858824 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1278546 (The Pile)

Max Activating Token Index: 109

Text #3

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1488790 (The Pile)

Max Activating Token Index: 657

Text #4

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.3336. Min Act: -0.0000

Data Index: 998529 (The Pile)

Max Activating Token Index: 89

Text #5

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1813507 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.4655. Min Act: -0.0000

Data Index: 1731580 (The Pile)

Max Activating Token Index: 438

Text #7

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.3282. Min Act: -0.0000

Data Index: 938984 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.3984. Min Act: -0.0000

Data Index: 323645 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.3746. Min Act: -0.0000

Data Index: 431353 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2785. Min Act: -0.0000

Data Index: 1639548 (The Pile)

Max Activating Token Index: 824

Text #11

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.3377. Min Act: -0.0000

Data Index: 377239 (The Pile)

Max Activating Token Index: 143

Text #12

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.4243. Min Act: -0.0000

Data Index: 1841820 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2017. Min Act: -0.0000

Data Index: 45977 (The Pile)

Max Activating Token Index: 711

Text #14

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.3966. Min Act: -0.0000

Data Index: 1091435 (The Pile)

Max Activating Token Index: 204

Text #15

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2515. Min Act: -0.0000

Data Index: 1977323 (The Pile)

Max Activating Token Index: 453

Text #16

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2496. Min Act: -0.0000

Data Index: 875374 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2645. Min Act: -0.0000

Data Index: 224252 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2302. Min Act: -0.0000

Data Index: 1234903 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.3132. Min Act: -0.0000

Data Index: 801238 (The Pile)

Max Activating Token Index: 843