Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5116 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.2019. Min Act: -0.0000

Data Index: 889412 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.2054. Min Act: -0.0000

Data Index: 737467 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.2017. Min Act: -0.0000

Data Index: 182532 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1174934 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1734. Min Act: -0.0000

Data Index: 352568 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1659. Min Act: -0.0000

Data Index: 547301 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1657. Min Act: -0.0000

Data Index: 392538 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1642. Min Act: -0.0000

Data Index: 433151 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1161604 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1729. Min Act: -0.0000

Data Index: 738064 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1559. Min Act: -0.0000

Data Index: 579090 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1112162 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1118036 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1643. Min Act: 0.0000

Data Index: 1144781 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1577. Min Act: -0.0000

Data Index: 484013 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1612. Min Act: -0.0000

Data Index: 179545 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1417. Min Act: -0.0000

Data Index: 528246 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1170099 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1340. Min Act: -0.0000

Data Index: 178846 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1501. Min Act: -0.0000

Data Index: 871047 (C4 (Web Text))

Max Activating Token Index: 866