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

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

Neuron 2652 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: 0.1804. Min Range: -0.1804

Max Act: 0.1804. Min Act: -0.0000

Data Index: 81469 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0906. Min Act: -0.0000

Data Index: 221856 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1293151 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0722. Min Act: -0.0000

Data Index: 690669 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0731. Min Act: -0.0000

Data Index: 836366 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0711. Min Act: -0.0000

Data Index: 469061 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0676. Min Act: -0.0000

Data Index: 854008 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0748. Min Act: -0.0000

Data Index: 283661 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0574. Min Act: -0.0000

Data Index: 948394 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0664. Min Act: -0.0000

Data Index: 438225 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0633. Min Act: -0.0000

Data Index: 327555 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1648064 (Python Code)

Max Activating Token Index: 217

Text #12

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0554. Min Act: -0.0000

Data Index: 676335 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0612. Min Act: -0.0000

Data Index: 64080 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0551. Min Act: -0.0000

Data Index: 59246 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0565. Min Act: -0.0000

Data Index: 849600 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0548. Min Act: -0.0000

Data Index: 457541 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0539. Min Act: -0.0000

Data Index: 429318 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0557. Min Act: -0.0000

Data Index: 474942 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.0617. Min Act: -0.0000

Data Index: 950566 (C4 (Web Text))

Max Activating Token Index: 770