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

Dataset: The Pile

Neuron 953 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: 1.2339. Min Range: -1.2339

Max Act: 1.2339. Min Act: -0.0000

Data Index: 1313027 (The Pile)

Max Activating Token Index: 539

Text #1

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.0634. Min Act: -0.0000

Data Index: 1294363 (The Pile)

Max Activating Token Index: 51

Text #2

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.0023. Min Act: -0.0000

Data Index: 673875 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9918. Min Act: -0.0000

Data Index: 161671 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8644. Min Act: -0.0000

Data Index: 668676 (The Pile)

Max Activating Token Index: 503

Text #5

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1587127 (The Pile)

Max Activating Token Index: 919

Text #6

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8575. Min Act: -0.0000

Data Index: 216077 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9535. Min Act: -0.0000

Data Index: 272478 (The Pile)

Max Activating Token Index: 196

Text #8

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1847240 (The Pile)

Max Activating Token Index: 606

Text #9

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1278314 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1330648 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8056. Min Act: -0.0000

Data Index: 390220 (The Pile)

Max Activating Token Index: 330

Text #12

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1796776 (The Pile)

Max Activating Token Index: 362

Text #13

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8744. Min Act: -0.0000

Data Index: 940668 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7679. Min Act: -0.0000

Data Index: 758659 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7785. Min Act: -0.0000

Data Index: 397884 (The Pile)

Max Activating Token Index: 755

Text #16

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8025. Min Act: -0.0000

Data Index: 931216 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1203687 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1882528 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7487. Min Act: -0.0000

Data Index: 623239 (The Pile)

Max Activating Token Index: 321