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

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

Neuron 888 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0001

Data Index: 456264 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0991. Min Act: -0.0001

Data Index: 221934 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0754. Min Act: -0.0001

Data Index: 943717 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1372248 (Python Code)

Max Activating Token Index: 960

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1095798 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1564694 (Python Code)

Max Activating Token Index: 872

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0829. Min Act: -0.0001

Data Index: 642062 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1477479 (Python Code)

Max Activating Token Index: 650

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0803. Min Act: -0.0001

Data Index: 191630 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0774. Min Act: -0.0001

Data Index: 115841 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1119830 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1516349 (Python Code)

Max Activating Token Index: 1013

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1595540 (Python Code)

Max Activating Token Index: 817

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1207480 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0760. Min Act: -0.0001

Data Index: 428248 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0794. Min Act: -0.0001

Data Index: 775096 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0757. Min Act: -0.0001

Data Index: 25639 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1512200 (Python Code)

Max Activating Token Index: 587

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0684. Min Act: -0.0001

Data Index: 40593 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1374415 (Python Code)

Max Activating Token Index: 110