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

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

Neuron 2071 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0728. Min Range: -3.0728

Max Act: 3.0728. Min Act: -0.0001

Data Index: 1491819 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 3.0728. Min Range: -3.0728

Max Act: 3.0728. Min Act: -0.0001

Data Index: 1613710 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 3.0728. Min Range: -3.0728

Max Act: 3.0728. Min Act: -0.0001

Data Index: 1375846 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 3.0728. Min Range: -3.0728

Max Act: 3.0728. Min Act: -0.0001

Data Index: 1490860 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 3.0728. Min Range: -3.0728

Max Act: 3.0728. Min Act: -0.0001

Data Index: 1580783 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 3.0728. Min Range: -3.0728

Max Act: 3.0728. Min Act: -0.0001

Data Index: 1513645 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 3.0728. Min Range: -3.0728

Max Act: 3.0728. Min Act: -0.0001

Data Index: 1594267 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 3.0728. Min Range: -3.0728

Max Act: 3.0728. Min Act: -0.0001

Data Index: 1486265 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 3.0728. Min Range: -3.0728

Max Act: 3.0728. Min Act: -0.0001

Data Index: 1428343 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 3.0728. Min Range: -3.0728

Max Act: 3.0728. Min Act: -0.0001

Data Index: 1524886 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.8923. Min Act: -0.0001

Data Index: 1438194 (Python Code)

Max Activating Token Index: 58

Text #11

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.8459. Min Act: -0.0001

Data Index: 1437224 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.8459. Min Act: -0.0001

Data Index: 1596819 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.8127. Min Act: -0.0001

Data Index: 1416277 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.6593. Min Act: -0.0001

Data Index: 1566040 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.7698. Min Act: -0.0001

Data Index: 1517710 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.5866. Min Act: -0.0001

Data Index: 1476728 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.5741. Min Act: -0.0001

Data Index: 1607548 (Python Code)

Max Activating Token Index: 891

Text #18

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.3725. Min Act: -0.0001

Data Index: 1559395 (Python Code)

Max Activating Token Index: 783

Text #19

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.4939. Min Act: -0.0001

Data Index: 1465474 (Python Code)

Max Activating Token Index: 3