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

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

Neuron 16 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.9687. Min Act: -0.0000

Data Index: 943948 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.5698. Min Act: -0.0001

Data Index: 150118 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 3.9687. Min Range: -3.9687

Max Act: 2.9626. Min Act: -0.0000

Data Index: 623261 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.2091. Min Act: -0.0000

Data Index: 1242447 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.5771. Min Act: -0.0001

Data Index: 718788 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.2240. Min Act: -0.0000

Data Index: 774638 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.8426. Min Act: -0.0001

Data Index: 992965 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 3.9687. Min Range: -3.9687

Max Act: 2.8061. Min Act: -0.0000

Data Index: 138907 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.3611. Min Act: -0.0000

Data Index: 450024 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.2080. Min Act: -0.0001

Data Index: 132860 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.3158. Min Act: -0.0001

Data Index: 19453 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.7698. Min Act: -0.0000

Data Index: 744729 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 3.9687. Min Range: -3.9687

Max Act: 2.8374. Min Act: -0.0001

Data Index: 106262 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.4429. Min Act: -0.0001

Data Index: 85780 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.1977. Min Act: -0.0000

Data Index: 879611 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 3.9687. Min Range: -3.9687

Max Act: 2.5740. Min Act: -0.0000

Data Index: 77851 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.0826. Min Act: -0.0000

Data Index: 1242668 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.1958. Min Act: -0.0000

Data Index: 349672 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.2160. Min Act: -0.0000

Data Index: 514766 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 3.9687. Min Range: -3.9687

Max Act: 2.7647. Min Act: -0.0000

Data Index: 680783 (C4 (Web Text))

Max Activating Token Index: 42