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

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

Neuron 1580 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: 2.5181. Min Range: -2.5181

Max Act: 2.5181. Min Act: -0.0000

Data Index: 1474340 (Python Code)

Max Activating Token Index: 575

Text #1

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.3695. Min Act: -0.0000

Data Index: 1520510 (Python Code)

Max Activating Token Index: 374

Text #2

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.4919. Min Act: -0.0000

Data Index: 1420167 (Python Code)

Max Activating Token Index: 882

Text #3

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.3866. Min Act: -0.0000

Data Index: 1391960 (Python Code)

Max Activating Token Index: 738

Text #4

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.3216. Min Act: -0.0000

Data Index: 1456185 (Python Code)

Max Activating Token Index: 619

Text #5

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.1780. Min Act: -0.0000

Data Index: 1435456 (Python Code)

Max Activating Token Index: 326

Text #6

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.0905. Min Act: -0.0000

Data Index: 1413316 (Python Code)

Max Activating Token Index: 787

Text #7

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.1998. Min Act: -0.0000

Data Index: 1117708 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.1435. Min Act: -0.0000

Data Index: 1590449 (Python Code)

Max Activating Token Index: 1012

Text #9

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.0402. Min Act: -0.0000

Data Index: 234768 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.1465. Min Act: -0.0000

Data Index: 1438607 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.1202. Min Act: -0.0000

Data Index: 1517609 (Python Code)

Max Activating Token Index: 718

Text #12

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.0995. Min Act: -0.0000

Data Index: 1149197 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.1051. Min Act: -0.0000

Data Index: 1473530 (Python Code)

Max Activating Token Index: 202

Text #14

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.2119. Min Act: -0.0000

Data Index: 1575318 (Python Code)

Max Activating Token Index: 578

Text #15

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.0914. Min Act: -0.0000

Data Index: 1362468 (Python Code)

Max Activating Token Index: 683

Text #16

Max Range: 2.5181. Min Range: -2.5181

Max Act: 1.9600. Min Act: -0.0000

Data Index: 1378067 (Python Code)

Max Activating Token Index: 957

Text #17

Max Range: 2.5181. Min Range: -2.5181

Max Act: 2.1942. Min Act: -0.0000

Data Index: 1510273 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 2.5181. Min Range: -2.5181

Max Act: 1.9905. Min Act: -0.0000

Data Index: 1366529 (Python Code)

Max Activating Token Index: 858

Text #19

Max Range: 2.5181. Min Range: -2.5181

Max Act: 1.8872. Min Act: -0.0000

Data Index: 1484112 (Python Code)

Max Activating Token Index: 105