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

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

Neuron 2323 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5000. Min Range: -1.5000

Max Act: 1.5000. Min Act: -0.0000

Data Index: 1541981 (Python Code)

Max Activating Token Index: 156

Text #1

Max Range: 1.5000. Min Range: -1.5000

Max Act: 1.1868. Min Act: -0.0000

Data Index: 1537525 (Python Code)

Max Activating Token Index: 654

Text #2

Max Range: 1.5000. Min Range: -1.5000

Max Act: 1.0835. Min Act: -0.0000

Data Index: 1403054 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 1.5000. Min Range: -1.5000

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1632751 (Python Code)

Max Activating Token Index: 776

Text #4

Max Range: 1.5000. Min Range: -1.5000

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1603211 (Python Code)

Max Activating Token Index: 690

Text #5

Max Range: 1.5000. Min Range: -1.5000

Max Act: 1.0381. Min Act: -0.0000

Data Index: 1396969 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1638818 (Python Code)

Max Activating Token Index: 586

Text #7

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1508671 (Python Code)

Max Activating Token Index: 242

Text #8

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1446789 (Python Code)

Max Activating Token Index: 105

Text #9

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1462802 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1387395 (Python Code)

Max Activating Token Index: 487

Text #11

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1532607 (Python Code)

Max Activating Token Index: 219

Text #12

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1526120 (Python Code)

Max Activating Token Index: 220

Text #13

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.8515. Min Act: -0.0000

Data Index: 1558108 (Python Code)

Max Activating Token Index: 378

Text #14

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1617913 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1533328 (Python Code)

Max Activating Token Index: 265

Text #16

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1565717 (Python Code)

Max Activating Token Index: 250

Text #17

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1512649 (Python Code)

Max Activating Token Index: 83

Text #18

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.8003. Min Act: -0.0000

Data Index: 1562456 (Python Code)

Max Activating Token Index: 148

Text #19

Max Range: 1.5000. Min Range: -1.5000

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1628921 (Python Code)

Max Activating Token Index: 33