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

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

Neuron 3456 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1087. Min Range: -1.1087

Max Act: 1.1087. Min Act: -0.0001

Data Index: 1594180 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 1.1087. Min Range: -1.1087

Max Act: 1.1087. Min Act: -0.0001

Data Index: 1540652 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 1.1087. Min Range: -1.1087

Max Act: 1.1087. Min Act: -0.0001

Data Index: 1484332 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 1.1087. Min Range: -1.1087

Max Act: 1.1087. Min Act: -0.0001

Data Index: 1632408 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 1.1087. Min Range: -1.1087

Max Act: 1.1087. Min Act: -0.0001

Data Index: 1362448 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 1.1087. Min Range: -1.1087

Max Act: 1.1087. Min Act: -0.0001

Data Index: 1530585 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 1.1087. Min Range: -1.1087

Max Act: 1.1087. Min Act: -0.0001

Data Index: 1447750 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9930. Min Act: -0.0001

Data Index: 1537136 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9379. Min Act: -0.0001

Data Index: 1403118 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9276. Min Act: -0.0001

Data Index: 1400087 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9057. Min Act: -0.0001

Data Index: 1500535 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8920. Min Act: -0.0001

Data Index: 1560634 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8912. Min Act: -0.0001

Data Index: 1405308 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8912. Min Act: -0.0001

Data Index: 1616444 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9115. Min Act: -0.0001

Data Index: 1444843 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9326. Min Act: -0.0001

Data Index: 1386007 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8424. Min Act: -0.0001

Data Index: 1388581 (Python Code)

Max Activating Token Index: 373

Text #17

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8034. Min Act: -0.0001

Data Index: 1543261 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8082. Min Act: -0.0001

Data Index: 1443235 (Python Code)

Max Activating Token Index: 9

Text #19

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8003. Min Act: -0.0001

Data Index: 1512292 (Python Code)

Max Activating Token Index: 5