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

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

Neuron 2042 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2721. Min Range: -2.2721

Max Act: 2.2721. Min Act: -0.0000

Data Index: 530592 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 2.2721. Min Range: -2.2721

Max Act: 2.0931. Min Act: -0.0000

Data Index: 859270 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 2.2721. Min Range: -2.2721

Max Act: 2.1490. Min Act: -0.0000

Data Index: 985663 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.9618. Min Act: -0.0000

Data Index: 790336 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.8578. Min Act: -0.0000

Data Index: 1101675 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.9278. Min Act: -0.0000

Data Index: 407317 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.9141. Min Act: 0.0000

Data Index: 587171 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.7879. Min Act: -0.0000

Data Index: 78513 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.8353. Min Act: -0.0000

Data Index: 942483 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.7603. Min Act: -0.0000

Data Index: 1002013 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.8428. Min Act: -0.0000

Data Index: 1329764 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.9272. Min Act: -0.0000

Data Index: 933195 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.7911. Min Act: -0.0000

Data Index: 694203 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.7937. Min Act: -0.0000

Data Index: 503797 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.8086. Min Act: -0.0000

Data Index: 826115 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.9115. Min Act: -0.0000

Data Index: 198503 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.7817. Min Act: 0.0000

Data Index: 462338 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.7049. Min Act: -0.0000

Data Index: 75679 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.8023. Min Act: 0.0000

Data Index: 597488 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 2.2721. Min Range: -2.2721

Max Act: 1.7804. Min Act: -0.0000

Data Index: 676867 (C4 (Web Text))

Max Activating Token Index: 838