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

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

Neuron 4752 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1070. Min Range: -6.1070

Max Act: 6.0512. Min Act: -0.0000

Data Index: 1614219 (Python Code)

Max Activating Token Index: 702

Text #1

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.9121. Min Act: -0.0000

Data Index: 1450712 (Python Code)

Max Activating Token Index: 305

Text #2

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.8852. Min Act: -0.0000

Data Index: 1416229 (Python Code)

Max Activating Token Index: 313

Text #3

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.7665. Min Act: -0.0000

Data Index: 1611330 (Python Code)

Max Activating Token Index: 472

Text #4

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.7416. Min Act: -0.0000

Data Index: 1574414 (Python Code)

Max Activating Token Index: 354

Text #5

Max Range: 6.1070. Min Range: -6.1070

Max Act: 6.1070. Min Act: -0.0000

Data Index: 1564658 (Python Code)

Max Activating Token Index: 527

Text #6

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.8375. Min Act: -0.0000

Data Index: 1439557 (Python Code)

Max Activating Token Index: 573

Text #7

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.6198. Min Act: -0.0000

Data Index: 1527498 (Python Code)

Max Activating Token Index: 516

Text #8

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.5873. Min Act: -0.0000

Data Index: 1443930 (Python Code)

Max Activating Token Index: 77

Text #9

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.8387. Min Act: -0.0000

Data Index: 1546005 (Python Code)

Max Activating Token Index: 158

Text #10

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.5435. Min Act: -0.0000

Data Index: 1467391 (Python Code)

Max Activating Token Index: 168

Text #11

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.7843. Min Act: -0.0000

Data Index: 1525120 (Python Code)

Max Activating Token Index: 827

Text #12

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.5081. Min Act: -0.0000

Data Index: 1394471 (Python Code)

Max Activating Token Index: 412

Text #13

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.3213. Min Act: -0.0000

Data Index: 1375540 (Python Code)

Max Activating Token Index: 51

Text #14

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.1715. Min Act: -0.0000

Data Index: 1546675 (Python Code)

Max Activating Token Index: 308

Text #15

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.6385. Min Act: -0.0000

Data Index: 1469035 (Python Code)

Max Activating Token Index: 814

Text #16

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.6096. Min Act: -0.0000

Data Index: 1563077 (Python Code)

Max Activating Token Index: 48

Text #17

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.0119. Min Act: -0.0000

Data Index: 1385779 (Python Code)

Max Activating Token Index: 948

Text #18

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.1859. Min Act: -0.0000

Data Index: 1410193 (Python Code)

Max Activating Token Index: 341

Text #19

Max Range: 6.1070. Min Range: -6.1070

Max Act: 5.7194. Min Act: -0.0000

Data Index: 1457841 (Python Code)

Max Activating Token Index: 881