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

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

Neuron 5049 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3557. Min Range: -5.3557

Max Act: 5.3557. Min Act: -0.0000

Data Index: 1614837 (Python Code)

Max Activating Token Index: 70

Text #1

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.8084. Min Act: -0.0000

Data Index: 1395040 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.8576. Min Act: -0.0000

Data Index: 1576745 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.8046. Min Act: -0.0000

Data Index: 1580966 (Python Code)

Max Activating Token Index: 62

Text #4

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.5907. Min Act: -0.0000

Data Index: 1584530 (Python Code)

Max Activating Token Index: 131

Text #5

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.9558. Min Act: -0.0000

Data Index: 1647604 (Python Code)

Max Activating Token Index: 88

Text #6

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.9409. Min Act: -0.0000

Data Index: 1507112 (Python Code)

Max Activating Token Index: 82

Text #7

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.7262. Min Act: -0.0000

Data Index: 1378166 (Python Code)

Max Activating Token Index: 155

Text #8

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.7090. Min Act: -0.0000

Data Index: 1402424 (Python Code)

Max Activating Token Index: 96

Text #9

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.8861. Min Act: -0.0000

Data Index: 1549766 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.7155. Min Act: -0.0000

Data Index: 1456336 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.6875. Min Act: -0.0000

Data Index: 1483275 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.5111. Min Act: -0.0000

Data Index: 1431519 (Python Code)

Max Activating Token Index: 43

Text #13

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.5026. Min Act: -0.0000

Data Index: 1637262 (Python Code)

Max Activating Token Index: 133

Text #14

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.8477. Min Act: -0.0000

Data Index: 1580547 (Python Code)

Max Activating Token Index: 641

Text #15

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.8471. Min Act: -0.0000

Data Index: 1511930 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.5938. Min Act: -0.0000

Data Index: 1630637 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.5946. Min Act: -0.0000

Data Index: 1562455 (Python Code)

Max Activating Token Index: 126

Text #18

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.7482. Min Act: -0.0000

Data Index: 1361291 (Python Code)

Max Activating Token Index: 97

Text #19

Max Range: 5.3557. Min Range: -5.3557

Max Act: 4.3838. Min Act: -0.0000

Data Index: 1478077 (Python Code)

Max Activating Token Index: 282