Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3219 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0680. Min Range: -1.0680

Max Act: 1.0680. Min Act: -0.0001

Data Index: 1259697 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8826. Min Act: -0.0001

Data Index: 1025423 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8665. Min Act: -0.0001

Data Index: 252927 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8556. Min Act: -0.0001

Data Index: 589410 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8730. Min Act: -0.0001

Data Index: 1134590 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8903. Min Act: -0.0001

Data Index: 1230915 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8592. Min Act: -0.0000

Data Index: 420673 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8575. Min Act: -0.0001

Data Index: 1215828 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8685. Min Act: -0.0001

Data Index: 717592 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8126. Min Act: -0.0001

Data Index: 1005902 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.9136. Min Act: -0.0001

Data Index: 1346257 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8418. Min Act: -0.0001

Data Index: 428049 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8325. Min Act: -0.0001

Data Index: 516307 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8296. Min Act: -0.0001

Data Index: 306274 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7144. Min Act: -0.0001

Data Index: 697489 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8738. Min Act: -0.0001

Data Index: 333996 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8080. Min Act: -0.0001

Data Index: 73184 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7740. Min Act: -0.0001

Data Index: 270440 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7889. Min Act: -0.0001

Data Index: 47407 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8308. Min Act: -0.0001

Data Index: 622705 (C4 (Web Text))

Max Activating Token Index: 835