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

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

Neuron 3983 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: 3.0749. Min Range: -3.0749

Max Act: 3.0749. Min Act: -0.0000

Data Index: 26779 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 3.0749. Min Range: -3.0749

Max Act: 2.8117. Min Act: -0.0000

Data Index: 419209 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 3.0749. Min Range: -3.0749

Max Act: 2.8543. Min Act: -0.0000

Data Index: 967278 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 3.0749. Min Range: -3.0749

Max Act: 2.1519. Min Act: -0.0000

Data Index: 411452 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 3.0749. Min Range: -3.0749

Max Act: 2.1837. Min Act: -0.0000

Data Index: 1255611 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.9569. Min Act: -0.0000

Data Index: 588004 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.8289. Min Act: -0.0000

Data Index: 855623 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.8289. Min Act: -0.0000

Data Index: 1323264 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.9206. Min Act: -0.0000

Data Index: 904209 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.8648. Min Act: -0.0000

Data Index: 1391895 (Python Code)

Max Activating Token Index: 583

Text #10

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.8591. Min Act: -0.0000

Data Index: 722769 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.5702. Min Act: -0.0000

Data Index: 811747 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.5641. Min Act: -0.0000

Data Index: 1169632 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.5552. Min Act: -0.0000

Data Index: 1266549 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.6484. Min Act: -0.0000

Data Index: 644223 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.6489. Min Act: -0.0000

Data Index: 741348 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.6048. Min Act: -0.0000

Data Index: 780043 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.5965. Min Act: -0.0000

Data Index: 613289 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.6046. Min Act: -0.0000

Data Index: 643695 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 3.0749. Min Range: -3.0749

Max Act: 1.3801. Min Act: -0.0000

Data Index: 842531 (C4 (Web Text))

Max Activating Token Index: 379