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

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

Neuron 5028 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0776. Min Act: -0.0000

Data Index: 73229 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1650262 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0636. Min Act: -0.0000

Data Index: 872323 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1217143 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1416532 (Python Code)

Max Activating Token Index: 240

Text #5

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0673. Min Act: -0.0000

Data Index: 841031 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0643. Min Act: -0.0000

Data Index: 216646 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0662. Min Act: -0.0000

Data Index: 822166 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0657. Min Act: -0.0000

Data Index: 531500 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1318632 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0607. Min Act: -0.0000

Data Index: 312698 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0628. Min Act: -0.0000

Data Index: 973628 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0620. Min Act: -0.0000

Data Index: 1537171 (Python Code)

Max Activating Token Index: 519

Text #13

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0593. Min Act: -0.0000

Data Index: 599223 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0609. Min Act: -0.0000

Data Index: 920071 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0563. Min Act: -0.0000

Data Index: 333487 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0545. Min Act: -0.0000

Data Index: 377607 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1353476 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0650. Min Act: -0.0000

Data Index: 793992 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.0776. Min Range: -0.0776

Max Act: 0.0605. Min Act: -0.0000

Data Index: 462979 (C4 (Web Text))

Max Activating Token Index: 791