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

Dataset: The Pile

Neuron 1650 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: 0.5212. Min Range: -0.5212

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1124088 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1973902 (The Pile)

Max Activating Token Index: 999

Text #2

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1741942 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4502. Min Act: -0.0000

Data Index: 423786 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4424. Min Act: -0.0000

Data Index: 523867 (The Pile)

Max Activating Token Index: 254

Text #5

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1369680 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4556. Min Act: -0.0000

Data Index: 41449 (The Pile)

Max Activating Token Index: 989

Text #7

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4264. Min Act: -0.0000

Data Index: 779523 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4084. Min Act: -0.0000

Data Index: 271525 (The Pile)

Max Activating Token Index: 763

Text #9

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3761. Min Act: -0.0000

Data Index: 598103 (The Pile)

Max Activating Token Index: 737

Text #10

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1966719 (The Pile)

Max Activating Token Index: 563

Text #11

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1958295 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1860273 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1229552 (The Pile)

Max Activating Token Index: 345

Text #14

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1172445 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1649418 (The Pile)

Max Activating Token Index: 495

Text #16

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1920636 (The Pile)

Max Activating Token Index: 706

Text #17

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4151. Min Act: -0.0000

Data Index: 268474 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1696385 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4110. Min Act: -0.0000

Data Index: 624530 (The Pile)

Max Activating Token Index: 881