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

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

Neuron 2791 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1397612 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8365. Min Act: -0.0001

Data Index: 1501670 (Python Code)

Max Activating Token Index: 918

Text #2

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7024. Min Act: -0.0000

Data Index: 35515 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6945. Min Act: -0.0001

Data Index: 1642167 (Python Code)

Max Activating Token Index: 885

Text #4

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1570186 (Python Code)

Max Activating Token Index: 799

Text #5

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6660. Min Act: -0.0001

Data Index: 1497872 (Python Code)

Max Activating Token Index: 239

Text #6

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1557475 (Python Code)

Max Activating Token Index: 480

Text #7

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1649196 (Python Code)

Max Activating Token Index: 570

Text #8

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.5879. Min Act: -0.0001

Data Index: 1579957 (Python Code)

Max Activating Token Index: 33

Text #9

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1479912 (Python Code)

Max Activating Token Index: 94

Text #10

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1194101 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1493857 (Python Code)

Max Activating Token Index: 284

Text #12

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.5774. Min Act: -0.0001

Data Index: 1395835 (Python Code)

Max Activating Token Index: 17

Text #13

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1443429 (Python Code)

Max Activating Token Index: 293

Text #14

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.5477. Min Act: -0.0001

Data Index: 1649403 (Python Code)

Max Activating Token Index: 89

Text #15

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.5378. Min Act: -0.0001

Data Index: 1633636 (Python Code)

Max Activating Token Index: 863

Text #16

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1414497 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.5493. Min Act: -0.0001

Data Index: 1650453 (Python Code)

Max Activating Token Index: 948

Text #18

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1369279 (Python Code)

Max Activating Token Index: 916

Text #19

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.5643. Min Act: -0.0001

Data Index: 1640698 (Python Code)

Max Activating Token Index: 97