Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1066 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1148. Min Act: -0.0003

Data Index: 1491811 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1017. Min Act: -0.0003

Data Index: 1421092 (Python Code)

Max Activating Token Index: 1002

Text #2

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0941. Min Act: -0.0003

Data Index: 1584694 (Python Code)

Max Activating Token Index: 892

Text #3

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0879. Min Act: -0.0003

Data Index: 1467896 (Python Code)

Max Activating Token Index: 538

Text #4

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0903. Min Act: -0.0003

Data Index: 1534397 (Python Code)

Max Activating Token Index: 679

Text #5

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0950. Min Act: -0.0003

Data Index: 1564566 (Python Code)

Max Activating Token Index: 347

Text #6

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0879. Min Act: -0.0003

Data Index: 1489159 (Python Code)

Max Activating Token Index: 752

Text #7

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0844. Min Act: -0.0003

Data Index: 1644248 (Python Code)

Max Activating Token Index: 1013

Text #8

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0836. Min Act: -0.0004

Data Index: 1653700 (Python Code)

Max Activating Token Index: 434

Text #9

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0814. Min Act: -0.0003

Data Index: 1494828 (Python Code)

Max Activating Token Index: 872

Text #10

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0811. Min Act: -0.0003

Data Index: 1523087 (Python Code)

Max Activating Token Index: 723

Text #11

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0845. Min Act: -0.0003

Data Index: 1438897 (Python Code)

Max Activating Token Index: 876

Text #12

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0811. Min Act: -0.0003

Data Index: 1541733 (Python Code)

Max Activating Token Index: 369

Text #13

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1417428 (Python Code)

Max Activating Token Index: 925

Text #14

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0797. Min Act: -0.0003

Data Index: 1640070 (Python Code)

Max Activating Token Index: 446

Text #15

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0819. Min Act: -0.0003

Data Index: 1366344 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0850. Min Act: -0.0003

Data Index: 1568187 (Python Code)

Max Activating Token Index: 425

Text #17

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0781. Min Act: -0.0003

Data Index: 382240 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0786. Min Act: -0.0003

Data Index: 1483887 (Python Code)

Max Activating Token Index: 534

Text #19

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0789. Min Act: -0.0003

Data Index: 9447 (C4 (Web Text))

Max Activating Token Index: 164