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

Dataset: The Pile

Neuron 796 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1997. Min Range: -1.1997

Max Act: 1.1997. Min Act: -0.0000

Data Index: 909522 (The Pile)

Max Activating Token Index: 961

Text #1

Max Range: 1.1997. Min Range: -1.1997

Max Act: 1.0193. Min Act: -0.0001

Data Index: 438938 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.9615. Min Act: -0.0001

Data Index: 1557379 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 1.1997. Min Range: -1.1997

Max Act: 1.0441. Min Act: -0.0000

Data Index: 163283 (The Pile)

Max Activating Token Index: 110

Text #4

Max Range: 1.1997. Min Range: -1.1997

Max Act: 1.1264. Min Act: -0.0001

Data Index: 1448204 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8821. Min Act: -0.0001

Data Index: 1665328 (The Pile)

Max Activating Token Index: 610

Text #6

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.9089. Min Act: -0.0000

Data Index: 798058 (The Pile)

Max Activating Token Index: 235

Text #7

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1546608 (The Pile)

Max Activating Token Index: 881

Text #8

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.9721. Min Act: -0.0001

Data Index: 71240 (The Pile)

Max Activating Token Index: 742

Text #9

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.7509. Min Act: -0.0001

Data Index: 1717373 (The Pile)

Max Activating Token Index: 600

Text #10

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8956. Min Act: -0.0001

Data Index: 678893 (The Pile)

Max Activating Token Index: 334

Text #11

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.9103. Min Act: -0.0000

Data Index: 249349 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1991064 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.7757. Min Act: -0.0001

Data Index: 1691088 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8531. Min Act: -0.0001

Data Index: 727907 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8191. Min Act: -0.0001

Data Index: 842064 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8324. Min Act: -0.0001

Data Index: 155368 (The Pile)

Max Activating Token Index: 914

Text #17

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8644. Min Act: -0.0001

Data Index: 783704 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1182890 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.9000. Min Act: -0.0000

Data Index: 32947 (The Pile)

Max Activating Token Index: 624