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

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

Neuron 2200 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: 2.7123. Min Range: -2.7123

Max Act: 2.7032. Min Act: -0.0000

Data Index: 1523501 (Python Code)

Max Activating Token Index: 243

Text #1

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.7123. Min Act: -0.0000

Data Index: 1571022 (Python Code)

Max Activating Token Index: 607

Text #2

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.6699. Min Act: -0.0000

Data Index: 1403590 (Python Code)

Max Activating Token Index: 872

Text #3

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.6498. Min Act: -0.0000

Data Index: 1607729 (Python Code)

Max Activating Token Index: 777

Text #4

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.1727. Min Act: -0.0000

Data Index: 1423843 (Python Code)

Max Activating Token Index: 441

Text #5

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.5189. Min Act: -0.0000

Data Index: 1378646 (Python Code)

Max Activating Token Index: 641

Text #6

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.6227. Min Act: -0.0000

Data Index: 1493665 (Python Code)

Max Activating Token Index: 962

Text #7

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.4987. Min Act: -0.0000

Data Index: 1363126 (Python Code)

Max Activating Token Index: 685

Text #8

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.3353. Min Act: -0.0000

Data Index: 1565330 (Python Code)

Max Activating Token Index: 242

Text #9

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.2787. Min Act: -0.0000

Data Index: 1550414 (Python Code)

Max Activating Token Index: 829

Text #10

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.0590. Min Act: -0.0000

Data Index: 1394433 (Python Code)

Max Activating Token Index: 889

Text #11

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.1477. Min Act: -0.0000

Data Index: 1449811 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.2586. Min Act: -0.0000

Data Index: 1429293 (Python Code)

Max Activating Token Index: 1005

Text #13

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.0721. Min Act: -0.0000

Data Index: 1487127 (Python Code)

Max Activating Token Index: 234

Text #14

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.0551. Min Act: -0.0000

Data Index: 1560050 (Python Code)

Max Activating Token Index: 654

Text #15

Max Range: 2.7123. Min Range: -2.7123

Max Act: 1.8887. Min Act: -0.0000

Data Index: 1588502 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 2.7123. Min Range: -2.7123

Max Act: 2.0034. Min Act: -0.0000

Data Index: 1592161 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 2.7123. Min Range: -2.7123

Max Act: 1.8919. Min Act: -0.0000

Data Index: 1407682 (Python Code)

Max Activating Token Index: 787

Text #18

Max Range: 2.7123. Min Range: -2.7123

Max Act: 1.8694. Min Act: -0.0000

Data Index: 1640953 (Python Code)

Max Activating Token Index: 205

Text #19

Max Range: 2.7123. Min Range: -2.7123

Max Act: 1.9792. Min Act: -0.0000

Data Index: 1634676 (Python Code)

Max Activating Token Index: 890