Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3872 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0002

Data Index: 43887 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0002

Data Index: 849729 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0002

Data Index: 577446 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0002

Data Index: 586238 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0002

Data Index: 251829 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0002

Data Index: 898311 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0003

Data Index: 501041 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0002

Data Index: 917434 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0002

Data Index: 704881 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0506. Min Act: -0.0002

Data Index: 659990 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0506. Min Act: -0.0002

Data Index: 350654 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0506. Min Act: -0.0003

Data Index: 980924 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0506. Min Act: -0.0003

Data Index: 1249410 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1585938 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0497. Min Act: -0.0002

Data Index: 431046 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0497. Min Act: -0.0002

Data Index: 625201 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0497. Min Act: -0.0002

Data Index: 360772 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0497. Min Act: -0.0002

Data Index: 851005 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0497. Min Act: -0.0002

Data Index: 297672 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1039166 (C4 (Web Text))

Max Activating Token Index: 1