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

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

Neuron 1501 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.9835. Min Act: -0.0000

Data Index: 1630060 (Python Code)

Max Activating Token Index: 631

Text #1

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6766. Min Act: -0.0000

Data Index: 1570141 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.5532. Min Act: -0.0000

Data Index: 1596712 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1630943 (Python Code)

Max Activating Token Index: 169

Text #4

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1580270 (Python Code)

Max Activating Token Index: 247

Text #5

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.8407. Min Act: -0.0000

Data Index: 861021 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1598513 (Python Code)

Max Activating Token Index: 169

Text #7

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1543837 (Python Code)

Max Activating Token Index: 158

Text #8

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1495461 (Python Code)

Max Activating Token Index: 301

Text #9

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1075915 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.8791. Min Act: -0.0000

Data Index: 512272 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1504365 (Python Code)

Max Activating Token Index: 658

Text #12

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1635261 (Python Code)

Max Activating Token Index: 717

Text #13

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1495077 (Python Code)

Max Activating Token Index: 714

Text #14

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1601680 (Python Code)

Max Activating Token Index: 302

Text #15

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1572330 (Python Code)

Max Activating Token Index: 107

Text #16

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1473474 (Python Code)

Max Activating Token Index: 400

Text #17

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1621334 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1458142 (Python Code)

Max Activating Token Index: 529

Text #19

Max Range: 1.9835. Min Range: -1.9835

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1602677 (Python Code)

Max Activating Token Index: 865