Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3649 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2217. Min Range: -3.2217

Max Act: 3.2217. Min Act: -0.0000

Data Index: 1030331 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.8264. Min Act: -0.0000

Data Index: 1066949 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.7618. Min Act: -0.0000

Data Index: 9615 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.5802. Min Act: -0.0000

Data Index: 325387 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.8137. Min Act: -0.0000

Data Index: 834244 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.6723. Min Act: -0.0000

Data Index: 975604 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.6510. Min Act: -0.0000

Data Index: 825485 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.6181. Min Act: -0.0000

Data Index: 513846 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.5800. Min Act: -0.0000

Data Index: 1244683 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.4964. Min Act: -0.0000

Data Index: 1185225 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.4394. Min Act: -0.0000

Data Index: 610723 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.4344. Min Act: -0.0000

Data Index: 877692 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.4030. Min Act: -0.0000

Data Index: 415778 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.3967. Min Act: -0.0000

Data Index: 366423 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.3667. Min Act: -0.0000

Data Index: 440512 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.2407. Min Act: -0.0000

Data Index: 1079834 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.2394. Min Act: -0.0000

Data Index: 220918 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.1752. Min Act: -0.0000

Data Index: 1031064 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.0957. Min Act: -0.0000

Data Index: 1169443 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 3.2217. Min Range: -3.2217

Max Act: 2.0996. Min Act: -0.0000

Data Index: 1471488 (Python Code)

Max Activating Token Index: 308