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

Dataset: The Pile

Neuron 1545 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: 0.5832. Min Range: -0.5832

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1861543 (The Pile)

Max Activating Token Index: 347

Text #1

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1123824 (The Pile)

Max Activating Token Index: 726

Text #2

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1005530 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1173605 (The Pile)

Max Activating Token Index: 200

Text #4

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4811. Min Act: -0.0000

Data Index: 7890 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1498420 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4822. Min Act: -0.0000

Data Index: 141447 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4896. Min Act: -0.0000

Data Index: 824734 (The Pile)

Max Activating Token Index: 89

Text #8

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4771. Min Act: -0.0000

Data Index: 335208 (The Pile)

Max Activating Token Index: 745

Text #9

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1192048 (The Pile)

Max Activating Token Index: 449

Text #10

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4665. Min Act: -0.0000

Data Index: 735550 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1592493 (The Pile)

Max Activating Token Index: 232

Text #12

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4256. Min Act: -0.0000

Data Index: 547481 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4559. Min Act: -0.0000

Data Index: 425167 (The Pile)

Max Activating Token Index: 392

Text #14

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4394. Min Act: -0.0000

Data Index: 825997 (The Pile)

Max Activating Token Index: 261

Text #15

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1565638 (The Pile)

Max Activating Token Index: 785

Text #16

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4512. Min Act: -0.0000

Data Index: 573099 (The Pile)

Max Activating Token Index: 703

Text #17

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4217. Min Act: -0.0000

Data Index: 385178 (The Pile)

Max Activating Token Index: 712

Text #18

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1136831 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 0.5832. Min Range: -0.5832

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1361175 (The Pile)

Max Activating Token Index: 891