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

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

Neuron 2978 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: 1.8843. Min Range: -1.8843

Max Act: 1.8843. Min Act: -0.0000

Data Index: 1404294 (Python Code)

Max Activating Token Index: 388

Text #1

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.7063. Min Act: -0.0000

Data Index: 1047396 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.7693. Min Act: -0.0000

Data Index: 1555757 (Python Code)

Max Activating Token Index: 616

Text #3

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.6898. Min Act: -0.0000

Data Index: 1372834 (Python Code)

Max Activating Token Index: 738

Text #4

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.7063. Min Act: -0.0000

Data Index: 1535982 (Python Code)

Max Activating Token Index: 908

Text #5

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.7821. Min Act: -0.0000

Data Index: 1386402 (Python Code)

Max Activating Token Index: 295

Text #6

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.6705. Min Act: -0.0000

Data Index: 1568230 (Python Code)

Max Activating Token Index: 454

Text #7

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.6636. Min Act: -0.0000

Data Index: 1401614 (Python Code)

Max Activating Token Index: 841

Text #8

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.6822. Min Act: -0.0000

Data Index: 1455539 (Python Code)

Max Activating Token Index: 252

Text #9

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.6428. Min Act: -0.0000

Data Index: 1421815 (Python Code)

Max Activating Token Index: 899

Text #10

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.6225. Min Act: -0.0000

Data Index: 1377744 (Python Code)

Max Activating Token Index: 601

Text #11

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.5877. Min Act: -0.0000

Data Index: 1451126 (Python Code)

Max Activating Token Index: 168

Text #12

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.6604. Min Act: -0.0000

Data Index: 1542624 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.5760. Min Act: -0.0001

Data Index: 1478245 (Python Code)

Max Activating Token Index: 505

Text #14

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.5621. Min Act: -0.0000

Data Index: 1605317 (Python Code)

Max Activating Token Index: 335

Text #15

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.5705. Min Act: -0.0000

Data Index: 56840 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.4223. Min Act: -0.0000

Data Index: 1122104 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.5214. Min Act: -0.0000

Data Index: 1630104 (Python Code)

Max Activating Token Index: 506

Text #18

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.4496. Min Act: -0.0000

Data Index: 1394457 (Python Code)

Max Activating Token Index: 154

Text #19

Max Range: 1.8843. Min Range: -1.8843

Max Act: 1.4906. Min Act: -0.0000

Data Index: 1591996 (Python Code)

Max Activating Token Index: 576