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

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

Neuron 35 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0618. Min Range: -1.0618

Max Act: 1.0618. Min Act: -0.0000

Data Index: 260337 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 1.0618. Min Range: -1.0618

Max Act: 1.0181. Min Act: -0.0000

Data Index: 381502 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.8862. Min Act: -0.0000

Data Index: 437859 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.9875. Min Act: -0.0000

Data Index: 153181 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1108473 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1061192 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.8081. Min Act: -0.0000

Data Index: 65357 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.8024. Min Act: -0.0000

Data Index: 361009 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.8287. Min Act: -0.0000

Data Index: 65600 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.7877. Min Act: -0.0000

Data Index: 575050 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.8045. Min Act: -0.0000

Data Index: 813252 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.7673. Min Act: -0.0000

Data Index: 568708 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.6971. Min Act: -0.0000

Data Index: 548718 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.7437. Min Act: -0.0000

Data Index: 190474 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.6975. Min Act: -0.0000

Data Index: 585054 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.6628. Min Act: -0.0000

Data Index: 343846 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1293483 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1212526 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1141500 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 1.0618. Min Range: -1.0618

Max Act: 0.6744. Min Act: -0.0000

Data Index: 699141 (C4 (Web Text))

Max Activating Token Index: 381