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

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

Neuron 5764 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0143. Min Range: -2.0143

Max Act: 2.0143. Min Act: -0.0000

Data Index: 651890 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.8674. Min Act: -0.0000

Data Index: 1488380 (Python Code)

Max Activating Token Index: 770

Text #2

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.9372. Min Act: -0.0000

Data Index: 285195 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.5695. Min Act: -0.0000

Data Index: 1635080 (Python Code)

Max Activating Token Index: 481

Text #4

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.6118. Min Act: -0.0000

Data Index: 169877 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.6433. Min Act: -0.0000

Data Index: 1520997 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.6289. Min Act: -0.0000

Data Index: 1583850 (Python Code)

Max Activating Token Index: 287

Text #7

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.5287. Min Act: -0.0000

Data Index: 1413181 (Python Code)

Max Activating Token Index: 409

Text #8

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.6233. Min Act: -0.0000

Data Index: 1485818 (Python Code)

Max Activating Token Index: 343

Text #9

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.5005. Min Act: -0.0000

Data Index: 1560697 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.4972. Min Act: -0.0000

Data Index: 1290776 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.5861. Min Act: -0.0000

Data Index: 464389 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.5523. Min Act: -0.0000

Data Index: 1506564 (Python Code)

Max Activating Token Index: 736

Text #13

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.5090. Min Act: -0.0000

Data Index: 1653738 (Python Code)

Max Activating Token Index: 781

Text #14

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1479188 (Python Code)

Max Activating Token Index: 998

Text #15

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.3350. Min Act: -0.0000

Data Index: 1023036 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.2376. Min Act: -0.0000

Data Index: 727586 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.3276. Min Act: -0.0000

Data Index: 1574705 (Python Code)

Max Activating Token Index: 419

Text #18

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.2874. Min Act: -0.0000

Data Index: 59155 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 2.0143. Min Range: -2.0143

Max Act: 1.3671. Min Act: -0.0000

Data Index: 755415 (C4 (Web Text))

Max Activating Token Index: 227