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

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

Neuron 1100 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: 1.0093. Min Range: -1.0093

Max Act: 1.0093. Min Act: -0.0001

Data Index: 1433243 (Python Code)

Max Activating Token Index: 591

Text #1

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8913. Min Act: -0.0001

Data Index: 1613958 (Python Code)

Max Activating Token Index: 32

Text #2

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.9043. Min Act: -0.0001

Data Index: 1511048 (Python Code)

Max Activating Token Index: 942

Text #3

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8854. Min Act: -0.0001

Data Index: 1364109 (Python Code)

Max Activating Token Index: 83

Text #4

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8141. Min Act: -0.0001

Data Index: 1523300 (Python Code)

Max Activating Token Index: 1018

Text #5

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8604. Min Act: -0.0001

Data Index: 1549236 (Python Code)

Max Activating Token Index: 397

Text #6

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8657. Min Act: -0.0001

Data Index: 1656986 (Python Code)

Max Activating Token Index: 867

Text #7

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8014. Min Act: -0.0001

Data Index: 1396783 (Python Code)

Max Activating Token Index: 118

Text #8

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7420. Min Act: -0.0001

Data Index: 1402975 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7805. Min Act: -0.0001

Data Index: 1605599 (Python Code)

Max Activating Token Index: 469

Text #10

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8015. Min Act: -0.0001

Data Index: 1397721 (Python Code)

Max Activating Token Index: 964

Text #11

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7692. Min Act: -0.0001

Data Index: 1381096 (Python Code)

Max Activating Token Index: 58

Text #12

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6880. Min Act: -0.0001

Data Index: 1522070 (Python Code)

Max Activating Token Index: 843

Text #13

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7786. Min Act: -0.0001

Data Index: 1570798 (Python Code)

Max Activating Token Index: 432

Text #14

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7466. Min Act: -0.0001

Data Index: 1506700 (Python Code)

Max Activating Token Index: 34

Text #15

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6981. Min Act: -0.0001

Data Index: 1410264 (Python Code)

Max Activating Token Index: 575

Text #16

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7433. Min Act: -0.0001

Data Index: 1379939 (Python Code)

Max Activating Token Index: 56

Text #17

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6901. Min Act: -0.0001

Data Index: 1378093 (Python Code)

Max Activating Token Index: 901

Text #18

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7052. Min Act: -0.0001

Data Index: 1630460 (Python Code)

Max Activating Token Index: 772

Text #19

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7005. Min Act: -0.0001

Data Index: 1428713 (Python Code)

Max Activating Token Index: 541