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

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

Neuron 4826 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.8837. Min Act: -0.0001

Data Index: 1618207 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.5508. Min Act: -0.0001

Data Index: 1442504 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.5412. Min Act: -0.0001

Data Index: 1426489 (Python Code)

Max Activating Token Index: 706

Text #3

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.5294. Min Act: -0.0001

Data Index: 1599741 (Python Code)

Max Activating Token Index: 397

Text #4

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.5284. Min Act: -0.0001

Data Index: 1445097 (Python Code)

Max Activating Token Index: 678

Text #5

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.5123. Min Act: -0.0001

Data Index: 1375100 (Python Code)

Max Activating Token Index: 277

Text #6

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4877. Min Act: -0.0001

Data Index: 1523879 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4886. Min Act: -0.0001

Data Index: 1446238 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4400. Min Act: -0.0001

Data Index: 1555680 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4426. Min Act: -0.0001

Data Index: 1396760 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4363. Min Act: -0.0001

Data Index: 1474604 (Python Code)

Max Activating Token Index: 280

Text #11

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4195. Min Act: -0.0001

Data Index: 1621619 (Python Code)

Max Activating Token Index: 126

Text #12

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4113. Min Act: -0.0001

Data Index: 1529422 (Python Code)

Max Activating Token Index: 105

Text #13

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.3989. Min Act: -0.0001

Data Index: 1448025 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.3985. Min Act: -0.0001

Data Index: 1421855 (Python Code)

Max Activating Token Index: 106

Text #15

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.3934. Min Act: -0.0001

Data Index: 1418391 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.4009. Min Act: -0.0001

Data Index: 1359907 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.3931. Min Act: -0.0001

Data Index: 1454621 (Python Code)

Max Activating Token Index: 982

Text #18

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.3930. Min Act: -0.0001

Data Index: 1369932 (Python Code)

Max Activating Token Index: 62

Text #19

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.3857. Min Act: -0.0001

Data Index: 1381622 (Python Code)

Max Activating Token Index: 31