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

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

Neuron 1877 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1129820 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1069643 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1240972 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1996. Min Act: -0.0000

Data Index: 690621 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1298870 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1757. Min Act: -0.0000

Data Index: 43978 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1868. Min Act: -0.0000

Data Index: 803247 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1367048 (Python Code)

Max Activating Token Index: 159

Text #8

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1888. Min Act: -0.0000

Data Index: 1146445 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1407652 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1376700 (Python Code)

Max Activating Token Index: 659

Text #11

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1538808 (Python Code)

Max Activating Token Index: 417

Text #12

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1778. Min Act: -0.0000

Data Index: 81772 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1418886 (Python Code)

Max Activating Token Index: 532

Text #14

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1549093 (Python Code)

Max Activating Token Index: 938

Text #15

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1549373 (Python Code)

Max Activating Token Index: 632

Text #16

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1436875 (Python Code)

Max Activating Token Index: 728

Text #17

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1468936 (Python Code)

Max Activating Token Index: 343

Text #18

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1479843 (Python Code)

Max Activating Token Index: 286

Text #19

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1730. Min Act: -0.0000

Data Index: 1652448 (Python Code)

Max Activating Token Index: 457