Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4249 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1535744 (Python Code)

Max Activating Token Index: 671

Text #1

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1371044 (Python Code)

Max Activating Token Index: 759

Text #2

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1396695 (Python Code)

Max Activating Token Index: 47

Text #3

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1435921 (Python Code)

Max Activating Token Index: 161

Text #4

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1457504 (Python Code)

Max Activating Token Index: 90

Text #5

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1366938 (Python Code)

Max Activating Token Index: 518

Text #6

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1430500 (Python Code)

Max Activating Token Index: 89

Text #7

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1656369 (Python Code)

Max Activating Token Index: 685

Text #8

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1430986 (Python Code)

Max Activating Token Index: 212

Text #9

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1436255 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1550311 (Python Code)

Max Activating Token Index: 615

Text #11

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1605713 (Python Code)

Max Activating Token Index: 733

Text #12

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1509981 (Python Code)

Max Activating Token Index: 203

Text #13

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1516379 (Python Code)

Max Activating Token Index: 77

Text #14

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1617689 (Python Code)

Max Activating Token Index: 204

Text #15

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1632809 (Python Code)

Max Activating Token Index: 59

Text #16

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1474731 (Python Code)

Max Activating Token Index: 596

Text #17

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1456231 (Python Code)

Max Activating Token Index: 272

Text #18

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1517535 (Python Code)

Max Activating Token Index: 498

Text #19

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1396242 (Python Code)

Max Activating Token Index: 309