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

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

Neuron 3682 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0090. Min Range: -1.0090

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1268958 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9506. Min Act: -0.0000

Data Index: 1587725 (Python Code)

Max Activating Token Index: 649

Text #2

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8607. Min Act: -0.0000

Data Index: 84837 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8619. Min Act: -0.0000

Data Index: 329386 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1060064 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9126. Min Act: -0.0000

Data Index: 577402 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7880. Min Act: -0.0000

Data Index: 943026 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1098069 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1427067 (Python Code)

Max Activating Token Index: 1000

Text #9

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.6863. Min Act: -0.0000

Data Index: 967177 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7786. Min Act: -0.0000

Data Index: 42581 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7115. Min Act: -0.0000

Data Index: 749059 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1269745 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1155191 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1120037 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7416. Min Act: -0.0000

Data Index: 969645 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.7362. Min Act: -0.0000

Data Index: 609742 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.6908. Min Act: -0.0000

Data Index: 74831 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.6860. Min Act: -0.0000

Data Index: 417508 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.6877. Min Act: -0.0000

Data Index: 150370 (C4 (Web Text))

Max Activating Token Index: 942