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

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

Neuron 683 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.8633. Min Act: -0.0000

Data Index: 761170 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7545. Min Act: -0.0000

Data Index: 4961 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7474. Min Act: -0.0000

Data Index: 488266 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7418. Min Act: -0.0000

Data Index: 888382 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7724. Min Act: -0.0000

Data Index: 504755 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7184. Min Act: -0.0000

Data Index: 945488 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6836. Min Act: -0.0000

Data Index: 57362 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6116. Min Act: -0.0000

Data Index: 129533 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6020. Min Act: -0.0000

Data Index: 768117 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1135233 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5942. Min Act: -0.0000

Data Index: 620195 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5935. Min Act: -0.0000

Data Index: 702494 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1290257 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5899. Min Act: -0.0000

Data Index: 360528 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5826. Min Act: -0.0000

Data Index: 250455 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1165889 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5980. Min Act: -0.0000

Data Index: 190099 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5835. Min Act: -0.0000

Data Index: 508827 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5783. Min Act: -0.0000

Data Index: 480674 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5385. Min Act: -0.0000

Data Index: 238219 (C4 (Web Text))

Max Activating Token Index: 84