Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 136 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1770916 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5753. Min Act: -0.0000

Data Index: 359803 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5067. Min Act: -0.0000

Data Index: 263035 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5151. Min Act: -0.0000

Data Index: 710425 (The Pile)

Max Activating Token Index: 754

Text #4

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1741319 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5655. Min Act: -0.0000

Data Index: 129514 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1988873 (The Pile)

Max Activating Token Index: 17

Text #7

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5232. Min Act: -0.0000

Data Index: 481535 (The Pile)

Max Activating Token Index: 924

Text #8

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1661313 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1479258 (The Pile)

Max Activating Token Index: 324

Text #10

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4854. Min Act: -0.0000

Data Index: 1889031 (The Pile)

Max Activating Token Index: 478

Text #11

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5214. Min Act: -0.0000

Data Index: 942208 (The Pile)

Max Activating Token Index: 730

Text #12

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1086039 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1417763 (The Pile)

Max Activating Token Index: 481

Text #14

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1731253 (The Pile)

Max Activating Token Index: 845

Text #15

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5843. Min Act: -0.0000

Data Index: 533517 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1701701 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1562192 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5069. Min Act: -0.0000

Data Index: 405706 (The Pile)

Max Activating Token Index: 208

Text #19

Max Range: 0.5843. Min Range: -0.5843

Max Act: 0.5216. Min Act: -0.0000

Data Index: 691964 (The Pile)

Max Activating Token Index: 13