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

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

Neuron 1435 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.7244. Min Act: -0.0000

Data Index: 1424355 (Python Code)

Max Activating Token Index: 598

Text #1

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.6118. Min Act: -0.0000

Data Index: 1414359 (Python Code)

Max Activating Token Index: 109

Text #2

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.6890. Min Act: -0.0000

Data Index: 1361308 (Python Code)

Max Activating Token Index: 150

Text #3

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.5838. Min Act: -0.0000

Data Index: 1558958 (Python Code)

Max Activating Token Index: 442

Text #4

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.4781. Min Act: -0.0000

Data Index: 1600808 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.4569. Min Act: -0.0000

Data Index: 1179983 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.4811. Min Act: -0.0000

Data Index: 1609457 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1395903 (Python Code)

Max Activating Token Index: 99

Text #8

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.3781. Min Act: -0.0000

Data Index: 1365502 (Python Code)

Max Activating Token Index: 498

Text #9

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.4593. Min Act: -0.0000

Data Index: 1550169 (Python Code)

Max Activating Token Index: 95

Text #10

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.4541. Min Act: -0.0000

Data Index: 1368732 (Python Code)

Max Activating Token Index: 967

Text #11

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.5461. Min Act: -0.0000

Data Index: 1646447 (Python Code)

Max Activating Token Index: 325

Text #12

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.3590. Min Act: -0.0000

Data Index: 1471210 (Python Code)

Max Activating Token Index: 573

Text #13

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.4290. Min Act: -0.0000

Data Index: 1621143 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.2590. Min Act: -0.0000

Data Index: 1601423 (Python Code)

Max Activating Token Index: 881

Text #15

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.3345. Min Act: -0.0000

Data Index: 1411759 (Python Code)

Max Activating Token Index: 703

Text #16

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.4056. Min Act: -0.0000

Data Index: 434257 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.3995. Min Act: -0.0000

Data Index: 1542716 (Python Code)

Max Activating Token Index: 57

Text #18

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.4819. Min Act: -0.0000

Data Index: 1611690 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.3101. Min Act: -0.0000

Data Index: 1563407 (Python Code)

Max Activating Token Index: 119