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

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

Neuron 3307 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.9650. Min Act: -0.0000

Data Index: 512304 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.3124. Min Act: -0.0000

Data Index: 633490 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.1384. Min Act: -0.0000

Data Index: 344218 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.0357. Min Act: -0.0000

Data Index: 582750 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1160542 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 1.9650. Min Range: -1.9650

Max Act: 0.9684. Min Act: -0.0000

Data Index: 183720 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1024770 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 1.9650. Min Range: -1.9650

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1350168 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.0174. Min Act: -0.0000

Data Index: 60132 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 1.9650. Min Range: -1.9650

Max Act: 0.9780. Min Act: -0.0000

Data Index: 938438 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 1.9650. Min Range: -1.9650

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1203330 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 1.9650. Min Range: -1.9650

Max Act: 0.8999. Min Act: -0.0000

Data Index: 103727 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 1.9650. Min Range: -1.9650

Max Act: 0.9214. Min Act: -0.0000

Data Index: 1255493 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 1.9650. Min Range: -1.9650

Max Act: 0.8701. Min Act: -0.0000

Data Index: 890273 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 1.9650. Min Range: -1.9650

Max Act: 0.8606. Min Act: -0.0000

Data Index: 14645 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 1.9650. Min Range: -1.9650

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1319130 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 1.9650. Min Range: -1.9650

Max Act: 0.8124. Min Act: -0.0000

Data Index: 769558 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 1.9650. Min Range: -1.9650

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1223835 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 1.9650. Min Range: -1.9650

Max Act: 0.7633. Min Act: -0.0000

Data Index: 609096 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 1.9650. Min Range: -1.9650

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1070053 (C4 (Web Text))

Max Activating Token Index: 20