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

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

Neuron 5183 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0030. Min Range: -4.0030

Max Act: 4.0030. Min Act: -0.0000

Data Index: 50802 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.6175. Min Act: -0.0000

Data Index: 106778 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.9049. Min Act: -0.0000

Data Index: 107418 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.8660. Min Act: -0.0000

Data Index: 62588 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.4957. Min Act: -0.0000

Data Index: 506532 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.4797. Min Act: -0.0000

Data Index: 916626 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.8814. Min Act: -0.0000

Data Index: 263092 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.6134. Min Act: -0.0000

Data Index: 514472 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.4186. Min Act: -0.0000

Data Index: 1270680 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.2255. Min Act: -0.0000

Data Index: 82827 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.2223. Min Act: -0.0000

Data Index: 231107 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.0035. Min Act: -0.0000

Data Index: 629752 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.2752. Min Act: -0.0000

Data Index: 351117 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.0969. Min Act: -0.0000

Data Index: 909625 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 4.0030. Min Range: -4.0030

Max Act: 2.8382. Min Act: -0.0000

Data Index: 861991 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.2339. Min Act: -0.0000

Data Index: 121507 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.0806. Min Act: -0.0000

Data Index: 928886 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 4.0030. Min Range: -4.0030

Max Act: 2.7732. Min Act: -0.0000

Data Index: 1052841 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 4.0030. Min Range: -4.0030

Max Act: 2.8917. Min Act: -0.0000

Data Index: 134747 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 4.0030. Min Range: -4.0030

Max Act: 3.1562. Min Act: -0.0000

Data Index: 83448 (C4 (Web Text))

Max Activating Token Index: 601