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

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

Neuron 4954 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0026. Min Range: -1.0026

Max Act: 1.0026. Min Act: -0.0001

Data Index: 1024088 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8876. Min Act: -0.0001

Data Index: 717456 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9138. Min Act: -0.0001

Data Index: 200666 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8744. Min Act: -0.0001

Data Index: 843689 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8702. Min Act: -0.0001

Data Index: 200543 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7727. Min Act: -0.0001

Data Index: 386712 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7706. Min Act: -0.0001

Data Index: 988319 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8228. Min Act: -0.0001

Data Index: 1324312 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7788. Min Act: -0.0001

Data Index: 341996 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7935. Min Act: -0.0001

Data Index: 1302443 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7120. Min Act: -0.0001

Data Index: 72851 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7791. Min Act: -0.0001

Data Index: 326412 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7517. Min Act: -0.0001

Data Index: 177886 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7508. Min Act: -0.0001

Data Index: 1228802 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7001. Min Act: -0.0001

Data Index: 105817 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7678. Min Act: -0.0001

Data Index: 33753 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7404. Min Act: -0.0001

Data Index: 274104 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7170. Min Act: -0.0001

Data Index: 881279 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7095. Min Act: -0.0001

Data Index: 52733 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.6816. Min Act: -0.0001

Data Index: 593326 (C4 (Web Text))

Max Activating Token Index: 417