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

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

Neuron 4706 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2743. Min Range: -2.2743

Max Act: 2.2743. Min Act: -0.0000

Data Index: 1545067 (Python Code)

Max Activating Token Index: 689

Text #1

Max Range: 2.2743. Min Range: -2.2743

Max Act: 2.1023. Min Act: -0.0000

Data Index: 1349834 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.9959. Min Act: -0.0000

Data Index: 879813 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.9855. Min Act: -0.0000

Data Index: 324811 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.9583. Min Act: -0.0000

Data Index: 448657 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 2.2743. Min Range: -2.2743

Max Act: 2.0008. Min Act: -0.0000

Data Index: 673482 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.8808. Min Act: -0.0000

Data Index: 276349 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.8615. Min Act: -0.0000

Data Index: 733006 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.8518. Min Act: -0.0000

Data Index: 1157326 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.8287. Min Act: -0.0000

Data Index: 1357389 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.8282. Min Act: -0.0000

Data Index: 991545 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.8188. Min Act: -0.0000

Data Index: 619973 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.7905. Min Act: -0.0000

Data Index: 7846 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.7894. Min Act: -0.0000

Data Index: 822914 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.8624. Min Act: -0.0000

Data Index: 1085563 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.7607. Min Act: -0.0000

Data Index: 686288 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.7665. Min Act: -0.0000

Data Index: 650558 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.7404. Min Act: -0.0000

Data Index: 1160586 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.8415. Min Act: -0.0000

Data Index: 965246 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 2.2743. Min Range: -2.2743

Max Act: 1.7388. Min Act: -0.0000

Data Index: 563909 (C4 (Web Text))

Max Activating Token Index: 895