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

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

Neuron 1711 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8532. Min Range: -3.8532

Max Act: 3.8532. Min Act: -0.0000

Data Index: 156541 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 3.8532. Min Range: -3.8532

Max Act: 3.5447. Min Act: -0.0000

Data Index: 1469373 (Python Code)

Max Activating Token Index: 755

Text #2

Max Range: 3.8532. Min Range: -3.8532

Max Act: 3.5525. Min Act: -0.0000

Data Index: 1110935 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 3.8532. Min Range: -3.8532

Max Act: 3.4538. Min Act: -0.0000

Data Index: 553773 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 3.8532. Min Range: -3.8532

Max Act: 3.3761. Min Act: -0.0000

Data Index: 902898 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 3.8532. Min Range: -3.8532

Max Act: 3.1965. Min Act: -0.0000

Data Index: 27771 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 3.8532. Min Range: -3.8532

Max Act: 3.3265. Min Act: 0.0000

Data Index: 1110706 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 3.8532. Min Range: -3.8532

Max Act: 3.3644. Min Act: -0.0000

Data Index: 89433 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 3.8532. Min Range: -3.8532

Max Act: 3.3058. Min Act: -0.0000

Data Index: 1057979 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 3.8532. Min Range: -3.8532

Max Act: 3.1407. Min Act: -0.0000

Data Index: 1027660 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 3.8532. Min Range: -3.8532

Max Act: 2.9314. Min Act: -0.0000

Data Index: 1389787 (Python Code)

Max Activating Token Index: 842

Text #11

Max Range: 3.8532. Min Range: -3.8532

Max Act: 3.0904. Min Act: -0.0000

Data Index: 1413267 (Python Code)

Max Activating Token Index: 648

Text #12

Max Range: 3.8532. Min Range: -3.8532

Max Act: 3.0553. Min Act: -0.0000

Data Index: 1631547 (Python Code)

Max Activating Token Index: 1006

Text #13

Max Range: 3.8532. Min Range: -3.8532

Max Act: 2.7551. Min Act: -0.0000

Data Index: 576262 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 3.8532. Min Range: -3.8532

Max Act: 2.7955. Min Act: -0.0000

Data Index: 1152942 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 3.8532. Min Range: -3.8532

Max Act: 2.8839. Min Act: -0.0000

Data Index: 233082 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 3.8532. Min Range: -3.8532

Max Act: 3.0351. Min Act: -0.0000

Data Index: 16224 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 3.8532. Min Range: -3.8532

Max Act: 2.8114. Min Act: -0.0000

Data Index: 1087164 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 3.8532. Min Range: -3.8532

Max Act: 2.6789. Min Act: -0.0000

Data Index: 1385429 (Python Code)

Max Activating Token Index: 161

Text #19

Max Range: 3.8532. Min Range: -3.8532

Max Act: 2.6518. Min Act: -0.0000

Data Index: 1496934 (Python Code)

Max Activating Token Index: 126