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

Dataset: The Pile

Neuron 1994 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: 0.9080. Min Range: -0.9080

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1968651 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.8183. Min Act: -0.0000

Data Index: 787315 (The Pile)

Max Activating Token Index: 512

Text #2

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7704. Min Act: -0.0000

Data Index: 1979966 (The Pile)

Max Activating Token Index: 523

Text #3

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7207. Min Act: -0.0000

Data Index: 15357 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7795. Min Act: -0.0000

Data Index: 350547 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7428. Min Act: -0.0000

Data Index: 16365 (The Pile)

Max Activating Token Index: 429

Text #6

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1732010 (The Pile)

Max Activating Token Index: 455

Text #7

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7025. Min Act: -0.0000

Data Index: 361209 (The Pile)

Max Activating Token Index: 268

Text #8

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7361. Min Act: -0.0000

Data Index: 513604 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1149356 (The Pile)

Max Activating Token Index: 515

Text #10

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1889207 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7020. Min Act: -0.0000

Data Index: 616932 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6422. Min Act: -0.0000

Data Index: 226137 (The Pile)

Max Activating Token Index: 86

Text #13

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1539976 (The Pile)

Max Activating Token Index: 1014

Text #14

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6366. Min Act: -0.0000

Data Index: 747541 (The Pile)

Max Activating Token Index: 711

Text #15

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6670. Min Act: -0.0000

Data Index: 514051 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1858556 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7298. Min Act: -0.0000

Data Index: 785003 (The Pile)

Max Activating Token Index: 345

Text #18

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6391. Min Act: -0.0000

Data Index: 426930 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1960088 (The Pile)

Max Activating Token Index: 864