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

Dataset: The Pile

Neuron 882 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7926. Min Range: -3.7926

Max Act: 3.7926. Min Act: -0.0000

Data Index: 1118078 (The Pile)

Max Activating Token Index: 528

Text #1

Max Range: 3.7926. Min Range: -3.7926

Max Act: 3.4866. Min Act: -0.0000

Data Index: 1669496 (The Pile)

Max Activating Token Index: 829

Text #2

Max Range: 3.7926. Min Range: -3.7926

Max Act: 3.2948. Min Act: -0.0000

Data Index: 831393 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 3.7926. Min Range: -3.7926

Max Act: 3.2277. Min Act: -0.0000

Data Index: 291040 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 3.7926. Min Range: -3.7926

Max Act: 3.1928. Min Act: -0.0000

Data Index: 714529 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 3.7926. Min Range: -3.7926

Max Act: 3.0099. Min Act: -0.0000

Data Index: 1625813 (The Pile)

Max Activating Token Index: 947

Text #6

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.8501. Min Act: -0.0000

Data Index: 1652051 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.7899. Min Act: -0.0000

Data Index: 848453 (The Pile)

Max Activating Token Index: 434

Text #8

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.7452. Min Act: -0.0000

Data Index: 1733177 (The Pile)

Max Activating Token Index: 584

Text #9

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.7276. Min Act: -0.0000

Data Index: 376275 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.6441. Min Act: -0.0000

Data Index: 312208 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.6222. Min Act: -0.0000

Data Index: 32704 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.5963. Min Act: -0.0000

Data Index: 1981923 (The Pile)

Max Activating Token Index: 968

Text #13

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.5511. Min Act: -0.0000

Data Index: 850026 (The Pile)

Max Activating Token Index: 89

Text #14

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.5406. Min Act: -0.0000

Data Index: 1669402 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.5212. Min Act: -0.0000

Data Index: 1102756 (The Pile)

Max Activating Token Index: 555

Text #16

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.5127. Min Act: -0.0000

Data Index: 308366 (The Pile)

Max Activating Token Index: 695

Text #17

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.6464. Min Act: -0.0000

Data Index: 992972 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.4965. Min Act: -0.0000

Data Index: 85698 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 3.7926. Min Range: -3.7926

Max Act: 2.3611. Min Act: -0.0000

Data Index: 1510503 (The Pile)

Max Activating Token Index: 447