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

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

Neuron 3330 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.4706. Min Act: -0.0000

Data Index: 1502470 (Python Code)

Max Activating Token Index: 434

Text #1

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.3935. Min Act: -0.0000

Data Index: 1538883 (Python Code)

Max Activating Token Index: 469

Text #2

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.4131. Min Act: -0.0000

Data Index: 1572964 (Python Code)

Max Activating Token Index: 115

Text #3

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.2950. Min Act: -0.0000

Data Index: 252795 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.2345. Min Act: -0.0000

Data Index: 141927 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1479320 (Python Code)

Max Activating Token Index: 413

Text #6

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.2055. Min Act: -0.0000

Data Index: 842165 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.2717. Min Act: -0.0000

Data Index: 175793 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.1843. Min Act: -0.0000

Data Index: 549442 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.1753. Min Act: -0.0000

Data Index: 308935 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.1909. Min Act: -0.0000

Data Index: 1518490 (Python Code)

Max Activating Token Index: 301

Text #11

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1450283 (Python Code)

Max Activating Token Index: 251

Text #12

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.1112. Min Act: -0.0000

Data Index: 1585904 (Python Code)

Max Activating Token Index: 176

Text #13

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.1289. Min Act: -0.0000

Data Index: 70413 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.0880. Min Act: -0.0000

Data Index: 593033 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.1272. Min Act: -0.0000

Data Index: 1543088 (Python Code)

Max Activating Token Index: 690

Text #16

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.0803. Min Act: -0.0000

Data Index: 1489566 (Python Code)

Max Activating Token Index: 513

Text #17

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1521908 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.0726. Min Act: -0.0000

Data Index: 1361696 (Python Code)

Max Activating Token Index: 753

Text #19

Max Range: 1.4706. Min Range: -1.4706

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1475049 (Python Code)

Max Activating Token Index: 727