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

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

Neuron 3436 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: 0.8272. Min Range: -0.8272

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1509675 (Python Code)

Max Activating Token Index: 670

Text #1

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1412239 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1460540 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1448411 (Python Code)

Max Activating Token Index: 228

Text #4

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6866. Min Act: -0.0001

Data Index: 1544412 (Python Code)

Max Activating Token Index: 535

Text #5

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1593591 (Python Code)

Max Activating Token Index: 562

Text #6

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1475232 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1606306 (Python Code)

Max Activating Token Index: 1008

Text #8

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1445027 (Python Code)

Max Activating Token Index: 215

Text #9

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6601. Min Act: 0.0000

Data Index: 1655155 (Python Code)

Max Activating Token Index: 75

Text #10

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1409275 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1526119 (Python Code)

Max Activating Token Index: 695

Text #12

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1416911 (Python Code)

Max Activating Token Index: 710

Text #13

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1571273 (Python Code)

Max Activating Token Index: 286

Text #14

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6072. Min Act: -0.0001

Data Index: 1425202 (Python Code)

Max Activating Token Index: 1004

Text #15

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6063. Min Act: 0.0000

Data Index: 1478180 (Python Code)

Max Activating Token Index: 336

Text #16

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1600387 (Python Code)

Max Activating Token Index: 223

Text #17

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1411194 (Python Code)

Max Activating Token Index: 142

Text #18

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1646388 (Python Code)

Max Activating Token Index: 461

Text #19

Max Range: 0.8272. Min Range: -0.8272

Max Act: 0.6430. Min Act: 0.0000

Data Index: 1506949 (Python Code)

Max Activating Token Index: 72