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

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

Neuron 1091 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: 0.6744. Min Range: -0.6744

Max Act: 0.6744. Min Act: -0.0000

Data Index: 472941 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5468. Min Act: -0.0000

Data Index: 411061 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5692. Min Act: -0.0000

Data Index: 877058 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1313817 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5258. Min Act: -0.0000

Data Index: 225571 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.6159. Min Act: -0.0000

Data Index: 990696 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5197. Min Act: -0.0000

Data Index: 613153 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5709. Min Act: -0.0000

Data Index: 931700 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1054865 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1161923 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5840. Min Act: -0.0000

Data Index: 420380 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5260. Min Act: -0.0000

Data Index: 571191 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1169606 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.4233. Min Act: -0.0000

Data Index: 916439 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.3895. Min Act: -0.0000

Data Index: 330793 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.3549. Min Act: -0.0000

Data Index: 79650 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.3510. Min Act: -0.0000

Data Index: 572205 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1047661 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1075808 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.6744. Min Range: -0.6744

Max Act: 0.3018. Min Act: -0.0000

Data Index: 948474 (C4 (Web Text))

Max Activating Token Index: 669