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

Dataset: The Pile

Neuron 1608 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: 1.2904. Min Range: -1.2904

Max Act: 1.1927. Min Act: -0.0000

Data Index: 482045 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.2505. Min Act: -0.0000

Data Index: 1103884 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0272. Min Act: -0.0000

Data Index: 858847 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.1980. Min Act: 0.0000

Data Index: 1626188 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.1819. Min Act: 0.0000

Data Index: 1658036 (The Pile)

Max Activating Token Index: 429

Text #5

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0344. Min Act: -0.0000

Data Index: 495908 (The Pile)

Max Activating Token Index: 927

Text #6

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.1638. Min Act: -0.0000

Data Index: 464034 (The Pile)

Max Activating Token Index: 214

Text #7

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1380776 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.2904. Min Act: -0.0000

Data Index: 1264341 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0673. Min Act: -0.0000

Data Index: 10344 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0614. Min Act: -0.0000

Data Index: 603549 (The Pile)

Max Activating Token Index: 882

Text #11

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.1477. Min Act: -0.0000

Data Index: 1834783 (The Pile)

Max Activating Token Index: 989

Text #12

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1569238 (The Pile)

Max Activating Token Index: 803

Text #13

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0293. Min Act: -0.0000

Data Index: 1914894 (The Pile)

Max Activating Token Index: 367

Text #14

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1313535 (The Pile)

Max Activating Token Index: 413

Text #15

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0158. Min Act: -0.0000

Data Index: 1951888 (The Pile)

Max Activating Token Index: 652

Text #16

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0165. Min Act: 0.0000

Data Index: 915833 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.9485. Min Act: -0.0000

Data Index: 1731984 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0396. Min Act: -0.0000

Data Index: 172086 (The Pile)

Max Activating Token Index: 210

Text #19

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0767. Min Act: -0.0000

Data Index: 1956839 (The Pile)

Max Activating Token Index: 886