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

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

Neuron 2456 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.7641. Min Act: -0.0000

Data Index: 670961 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.7024. Min Act: -0.0000

Data Index: 471808 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6996. Min Act: -0.0000

Data Index: 144293 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.7052. Min Act: -0.0000

Data Index: 701040 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6745. Min Act: -0.0000

Data Index: 204051 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1248512 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6087. Min Act: -0.0000

Data Index: 735948 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6279. Min Act: -0.0000

Data Index: 884978 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6074. Min Act: -0.0000

Data Index: 6213 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6029. Min Act: -0.0000

Data Index: 801978 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1114092 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1197850 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5532. Min Act: -0.0000

Data Index: 856387 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5692. Min Act: -0.0000

Data Index: 88863 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5836. Min Act: -0.0000

Data Index: 995073 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5656. Min Act: -0.0000

Data Index: 412045 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5640. Min Act: -0.0000

Data Index: 523701 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5435. Min Act: 0.0000

Data Index: 1231964 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5617. Min Act: -0.0000

Data Index: 296625 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5568. Min Act: -0.0000

Data Index: 366528 (C4 (Web Text))

Max Activating Token Index: 850