Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2094 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1018466 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1115065 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1109244 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0949. Min Act: -0.0001

Data Index: 444223 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0942. Min Act: -0.0001

Data Index: 32860 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0871. Min Act: -0.0001

Data Index: 689263 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0872. Min Act: -0.0001

Data Index: 1081148 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0847. Min Act: -0.0001

Data Index: 626738 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1059140 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1019632 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0815. Min Act: -0.0001

Data Index: 274415 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0858. Min Act: -0.0001

Data Index: 44063 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0831. Min Act: -0.0001

Data Index: 448908 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1081256 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0789. Min Act: -0.0001

Data Index: 657580 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0792. Min Act: -0.0001

Data Index: 661638 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0735. Min Act: -0.0001

Data Index: 394981 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0770. Min Act: -0.0001

Data Index: 664153 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0826. Min Act: -0.0001

Data Index: 424006 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0738. Min Act: -0.0001

Data Index: 347744 (C4 (Web Text))

Max Activating Token Index: 198