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

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

Neuron 3767 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0030. Min Range: -3.0030

Max Act: 3.0012. Min Act: -0.0000

Data Index: 1551007 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 3.0030. Min Range: -3.0030

Max Act: 3.0027. Min Act: -0.0000

Data Index: 1466915 (Python Code)

Max Activating Token Index: 357

Text #2

Max Range: 3.0030. Min Range: -3.0030

Max Act: 3.0030. Min Act: -0.0001

Data Index: 1640634 (Python Code)

Max Activating Token Index: 222

Text #3

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.8342. Min Act: -0.0000

Data Index: 1640038 (Python Code)

Max Activating Token Index: 106

Text #4

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.8724. Min Act: -0.0000

Data Index: 1412791 (Python Code)

Max Activating Token Index: 895

Text #5

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.7030. Min Act: -0.0001

Data Index: 1369081 (Python Code)

Max Activating Token Index: 1014

Text #6

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.6826. Min Act: -0.0000

Data Index: 1525004 (Python Code)

Max Activating Token Index: 835

Text #7

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.8145. Min Act: -0.0000

Data Index: 1363697 (Python Code)

Max Activating Token Index: 696

Text #8

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.6321. Min Act: -0.0000

Data Index: 1550208 (Python Code)

Max Activating Token Index: 797

Text #9

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.2222. Min Act: -0.0001

Data Index: 1408557 (Python Code)

Max Activating Token Index: 749

Text #10

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.7303. Min Act: -0.0001

Data Index: 1620443 (Python Code)

Max Activating Token Index: 196

Text #11

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.6969. Min Act: -0.0001

Data Index: 1391392 (Python Code)

Max Activating Token Index: 126

Text #12

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.6934. Min Act: -0.0001

Data Index: 1548952 (Python Code)

Max Activating Token Index: 124

Text #13

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.7819. Min Act: -0.0001

Data Index: 1431923 (Python Code)

Max Activating Token Index: 514

Text #14

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.3891. Min Act: -0.0000

Data Index: 1563513 (Python Code)

Max Activating Token Index: 1007

Text #15

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.6142. Min Act: -0.0000

Data Index: 1471646 (Python Code)

Max Activating Token Index: 210

Text #16

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.5904. Min Act: -0.0000

Data Index: 1540080 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.5940. Min Act: -0.0001

Data Index: 1372533 (Python Code)

Max Activating Token Index: 818

Text #18

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.5716. Min Act: -0.0000

Data Index: 1638726 (Python Code)

Max Activating Token Index: 542

Text #19

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.4630. Min Act: -0.0001

Data Index: 1654438 (Python Code)

Max Activating Token Index: 274