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

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

Neuron 5672 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1112. Min Act: -0.0001

Data Index: 339352 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1570210 (Python Code)

Max Activating Token Index: 614

Text #2

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1478086 (Python Code)

Max Activating Token Index: 708

Text #3

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1432362 (Python Code)

Max Activating Token Index: 438

Text #4

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1629390 (Python Code)

Max Activating Token Index: 206

Text #5

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1389487 (Python Code)

Max Activating Token Index: 591

Text #6

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1416637 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0860. Min Act: -0.0000

Data Index: 1515759 (Python Code)

Max Activating Token Index: 336

Text #8

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1554787 (Python Code)

Max Activating Token Index: 263

Text #9

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1512942 (Python Code)

Max Activating Token Index: 723

Text #10

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0750. Min Act: -0.0000

Data Index: 1434340 (Python Code)

Max Activating Token Index: 793

Text #11

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1578703 (Python Code)

Max Activating Token Index: 995

Text #12

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1544789 (Python Code)

Max Activating Token Index: 161

Text #13

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0815. Min Act: -0.0000

Data Index: 1588384 (Python Code)

Max Activating Token Index: 552

Text #14

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1614070 (Python Code)

Max Activating Token Index: 640

Text #15

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0804. Min Act: -0.0001

Data Index: 1367418 (Python Code)

Max Activating Token Index: 711

Text #16

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1446632 (Python Code)

Max Activating Token Index: 505

Text #17

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1642194 (Python Code)

Max Activating Token Index: 314

Text #18

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1419627 (Python Code)

Max Activating Token Index: 441

Text #19

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1613884 (Python Code)

Max Activating Token Index: 926