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

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

Neuron 1186 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0759. Min Act: -0.0002

Data Index: 493790 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1381074 (Python Code)

Max Activating Token Index: 60

Text #2

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0758. Min Act: -0.0002

Data Index: 94290 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0688. Min Act: -0.0002

Data Index: 439709 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1504043 (Python Code)

Max Activating Token Index: 133

Text #5

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0686. Min Act: -0.0002

Data Index: 712152 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0718. Min Act: -0.0002

Data Index: 253602 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0573. Min Act: -0.0002

Data Index: 892906 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0532. Min Act: -0.0002

Data Index: 539024 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0615. Min Act: -0.0002

Data Index: 189604 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0558. Min Act: -0.0002

Data Index: 906500 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1036800 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0610. Min Act: -0.0002

Data Index: 911207 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0591. Min Act: -0.0002

Data Index: 475111 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0542. Min Act: -0.0002

Data Index: 645717 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0586. Min Act: -0.0002

Data Index: 980032 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1424705 (Python Code)

Max Activating Token Index: 981

Text #17

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0541. Min Act: -0.0002

Data Index: 961991 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1334845 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0541. Min Act: -0.0002

Data Index: 964462 (C4 (Web Text))

Max Activating Token Index: 189