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

Dataset: The Pile

Neuron 3476 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1090155 (The Pile)

Max Activating Token Index: 375

Text #1

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1041884 (The Pile)

Max Activating Token Index: 772

Text #2

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8506. Min Act: -0.0000

Data Index: 151149 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.8067. Min Act: -0.0000

Data Index: 873595 (The Pile)

Max Activating Token Index: 157

Text #4

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1410676 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.7394. Min Act: -0.0000

Data Index: 967486 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6508. Min Act: -0.0000

Data Index: 65067 (The Pile)

Max Activating Token Index: 185

Text #7

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1263453 (The Pile)

Max Activating Token Index: 940

Text #8

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1081761 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1416614 (The Pile)

Max Activating Token Index: 476

Text #10

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6225. Min Act: -0.0000

Data Index: 912809 (The Pile)

Max Activating Token Index: 408

Text #11

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6608. Min Act: -0.0000

Data Index: 854351 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1505529 (The Pile)

Max Activating Token Index: 642

Text #13

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1851993 (The Pile)

Max Activating Token Index: 218

Text #14

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1638499 (The Pile)

Max Activating Token Index: 806

Text #15

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1943162 (The Pile)

Max Activating Token Index: 233

Text #16

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1603064 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6109. Min Act: -0.0000

Data Index: 213907 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1837956 (The Pile)

Max Activating Token Index: 94

Text #19

Max Range: 0.9116. Min Range: -0.9116

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1627341 (The Pile)

Max Activating Token Index: 132