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

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

Neuron 5821 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: 0.5880. Min Range: -0.5880

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1453149 (Python Code)

Max Activating Token Index: 256

Text #1

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1494963 (Python Code)

Max Activating Token Index: 687

Text #2

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1371628 (Python Code)

Max Activating Token Index: 462

Text #3

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1624422 (Python Code)

Max Activating Token Index: 266

Text #4

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1472383 (Python Code)

Max Activating Token Index: 444

Text #5

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1595003 (Python Code)

Max Activating Token Index: 1008

Text #6

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1419589 (Python Code)

Max Activating Token Index: 898

Text #7

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1567458 (Python Code)

Max Activating Token Index: 635

Text #8

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1568026 (Python Code)

Max Activating Token Index: 572

Text #9

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1522278 (Python Code)

Max Activating Token Index: 482

Text #10

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1565762 (Python Code)

Max Activating Token Index: 624

Text #11

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1467890 (Python Code)

Max Activating Token Index: 254

Text #12

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4793. Min Act: -0.0000

Data Index: 1554104 (Python Code)

Max Activating Token Index: 973

Text #13

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1638408 (Python Code)

Max Activating Token Index: 807

Text #14

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1602841 (Python Code)

Max Activating Token Index: 1022

Text #15

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1419725 (Python Code)

Max Activating Token Index: 491

Text #16

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1375299 (Python Code)

Max Activating Token Index: 620

Text #17

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1549859 (Python Code)

Max Activating Token Index: 244

Text #18

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1518034 (Python Code)

Max Activating Token Index: 553

Text #19

Max Range: 0.5880. Min Range: -0.5880

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1461714 (Python Code)

Max Activating Token Index: 15