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

Dataset: The Pile

Neuron 4310 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: 0.7246. Min Range: -0.7246

Max Act: 0.7246. Min Act: -0.0000

Data Index: 252441 (The Pile)

Max Activating Token Index: 839

Text #1

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.7186. Min Act: -0.0000

Data Index: 185300 (The Pile)

Max Activating Token Index: 321

Text #2

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.6518. Min Act: -0.0000

Data Index: 230330 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1943706 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5278. Min Act: -0.0000

Data Index: 588591 (The Pile)

Max Activating Token Index: 825

Text #5

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1224293 (The Pile)

Max Activating Token Index: 130

Text #6

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1791891 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1880943 (The Pile)

Max Activating Token Index: 815

Text #8

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1017273 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5956. Min Act: -0.0000

Data Index: 661282 (The Pile)

Max Activating Token Index: 689

Text #10

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4835. Min Act: -0.0000

Data Index: 269447 (The Pile)

Max Activating Token Index: 460

Text #11

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5023. Min Act: -0.0000

Data Index: 784968 (The Pile)

Max Activating Token Index: 14

Text #12

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1742962 (The Pile)

Max Activating Token Index: 369

Text #13

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1994990 (The Pile)

Max Activating Token Index: 877

Text #14

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.5028. Min Act: -0.0000

Data Index: 58744 (The Pile)

Max Activating Token Index: 177

Text #15

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1695040 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1820363 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4827. Min Act: -0.0000

Data Index: 764371 (The Pile)

Max Activating Token Index: 111

Text #18

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4688. Min Act: -0.0000

Data Index: 935968 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 0.7246. Min Range: -0.7246

Max Act: 0.4959. Min Act: -0.0000

Data Index: 47465 (The Pile)

Max Activating Token Index: 41