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

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

Neuron 3167 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5914. Min Act: -0.0001

Data Index: 1417816 (Python Code)

Max Activating Token Index: 710

Text #1

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5229. Min Act: -0.0001

Data Index: 1563751 (Python Code)

Max Activating Token Index: 674

Text #2

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3982. Min Act: -0.0001

Data Index: 1643401 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5617. Min Act: -0.0001

Data Index: 1597815 (Python Code)

Max Activating Token Index: 982

Text #4

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4656. Min Act: -0.0001

Data Index: 1531298 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4928. Min Act: -0.0001

Data Index: 1407246 (Python Code)

Max Activating Token Index: 702

Text #6

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4814. Min Act: -0.0001

Data Index: 1641495 (Python Code)

Max Activating Token Index: 920

Text #7

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4761. Min Act: -0.0001

Data Index: 1495595 (Python Code)

Max Activating Token Index: 982

Text #8

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4659. Min Act: -0.0001

Data Index: 1501102 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4659. Min Act: -0.0001

Data Index: 1602750 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5283. Min Act: -0.0001

Data Index: 1362299 (Python Code)

Max Activating Token Index: 143

Text #11

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4929. Min Act: -0.0001

Data Index: 1459141 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4198. Min Act: -0.0001

Data Index: 1487212 (Python Code)

Max Activating Token Index: 285

Text #13

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4869. Min Act: -0.0001

Data Index: 1574056 (Python Code)

Max Activating Token Index: 691

Text #14

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4277. Min Act: -0.0001

Data Index: 1386383 (Python Code)

Max Activating Token Index: 216

Text #15

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4268. Min Act: -0.0001

Data Index: 1496358 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4941. Min Act: -0.0001

Data Index: 1367500 (Python Code)

Max Activating Token Index: 347

Text #17

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4901. Min Act: -0.0001

Data Index: 1585706 (Python Code)

Max Activating Token Index: 555

Text #18

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4568. Min Act: -0.0001

Data Index: 1541094 (Python Code)

Max Activating Token Index: 649

Text #19

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4142. Min Act: -0.0001

Data Index: 1538788 (Python Code)

Max Activating Token Index: 165