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

Dataset: The Pile

Neuron 3415 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1570530 (The Pile)

Max Activating Token Index: 685

Text #1

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1747426 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.9093. Min Act: -0.0000

Data Index: 904391 (The Pile)

Max Activating Token Index: 183

Text #3

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1412353 (The Pile)

Max Activating Token Index: 234

Text #4

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.5840. Min Act: -0.0000

Data Index: 495271 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1980953 (The Pile)

Max Activating Token Index: 128

Text #6

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.5496. Min Act: -0.0000

Data Index: 583454 (The Pile)

Max Activating Token Index: 213

Text #7

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.5690. Min Act: -0.0000

Data Index: 623486 (The Pile)

Max Activating Token Index: 304

Text #8

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1166478 (The Pile)

Max Activating Token Index: 74

Text #9

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.4981. Min Act: -0.0000

Data Index: 168284 (The Pile)

Max Activating Token Index: 836

Text #10

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.5521. Min Act: -0.0000

Data Index: 713610 (The Pile)

Max Activating Token Index: 82

Text #11

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1785292 (The Pile)

Max Activating Token Index: 352

Text #12

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.5477. Min Act: -0.0000

Data Index: 359169 (The Pile)

Max Activating Token Index: 87

Text #13

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.4957. Min Act: -0.0000

Data Index: 1047678 (The Pile)

Max Activating Token Index: 486

Text #14

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1368126 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1511477 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1178722 (The Pile)

Max Activating Token Index: 240

Text #17

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1946995 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1895669 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 0.9713. Min Range: -0.9713

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1774468 (The Pile)

Max Activating Token Index: 197