Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2263 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1819010 (The Pile)

Max Activating Token Index: 27

Text #1

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2978. Min Act: -0.0000

Data Index: 274596 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2727. Min Act: -0.0000

Data Index: 390266 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1847416 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1771379 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2487. Min Act: -0.0000

Data Index: 671155 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1997129 (The Pile)

Max Activating Token Index: 371

Text #7

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1841718 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1619197 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1265473 (The Pile)

Max Activating Token Index: 71

Text #10

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1467887 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2486. Min Act: -0.0000

Data Index: 976056 (The Pile)

Max Activating Token Index: 242

Text #12

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1941985 (The Pile)

Max Activating Token Index: 592

Text #13

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2372. Min Act: -0.0000

Data Index: 94147 (The Pile)

Max Activating Token Index: 861

Text #14

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2431. Min Act: -0.0000

Data Index: 897671 (The Pile)

Max Activating Token Index: 995

Text #15

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2495. Min Act: -0.0000

Data Index: 271381 (The Pile)

Max Activating Token Index: 270

Text #16

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1607904 (The Pile)

Max Activating Token Index: 804

Text #17

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2376. Min Act: -0.0000

Data Index: 455968 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1007155 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1528633 (The Pile)

Max Activating Token Index: 612