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

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

Neuron 1565 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: 0.0722. Min Range: -0.0722

Max Act: 0.0718. Min Act: -0.0003

Data Index: 534673 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0705. Min Act: -0.0003

Data Index: 250325 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1627738 (Python Code)

Max Activating Token Index: 825

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0003

Data Index: 1477319 (Python Code)

Max Activating Token Index: 889

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0623. Min Act: -0.0003

Data Index: 809982 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0638. Min Act: -0.0003

Data Index: 832013 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0643. Min Act: -0.0003

Data Index: 878207 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0649. Min Act: -0.0003

Data Index: 1610792 (Python Code)

Max Activating Token Index: 195

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0597. Min Act: -0.0003

Data Index: 995517 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0629. Min Act: -0.0003

Data Index: 823347 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0616. Min Act: -0.0003

Data Index: 1643890 (Python Code)

Max Activating Token Index: 359

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0606. Min Act: -0.0003

Data Index: 1650485 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0621. Min Act: -0.0003

Data Index: 939644 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0562. Min Act: -0.0003

Data Index: 764377 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1186375 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0566. Min Act: -0.0003

Data Index: 442091 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1561085 (Python Code)

Max Activating Token Index: 213

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0577. Min Act: -0.0003

Data Index: 1645655 (Python Code)

Max Activating Token Index: 882

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0586. Min Act: -0.0003

Data Index: 712323 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0602. Min Act: -0.0003

Data Index: 399576 (C4 (Web Text))

Max Activating Token Index: 49