Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 21 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4558. Min Act: -0.0001

Data Index: 1434634 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4161. Min Act: -0.0001

Data Index: 1437126 (Python Code)

Max Activating Token Index: 296

Text #2

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4202. Min Act: -0.0001

Data Index: 1520792 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3964. Min Act: -0.0001

Data Index: 1551909 (Python Code)

Max Activating Token Index: 108

Text #4

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4094. Min Act: -0.0001

Data Index: 1523723 (Python Code)

Max Activating Token Index: 39

Text #5

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3800. Min Act: -0.0001

Data Index: 1595504 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3928. Min Act: -0.0001

Data Index: 1572751 (Python Code)

Max Activating Token Index: 189

Text #7

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3913. Min Act: -0.0001

Data Index: 1579699 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3886. Min Act: -0.0001

Data Index: 1387628 (Python Code)

Max Activating Token Index: 209

Text #9

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3996. Min Act: -0.0001

Data Index: 1566918 (Python Code)

Max Activating Token Index: 981

Text #10

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3857. Min Act: -0.0001

Data Index: 1423644 (Python Code)

Max Activating Token Index: 97

Text #11

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3767. Min Act: -0.0001

Data Index: 1376094 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3910. Min Act: -0.0001

Data Index: 1618803 (Python Code)

Max Activating Token Index: 219

Text #13

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3764. Min Act: -0.0001

Data Index: 1485276 (Python Code)

Max Activating Token Index: 150

Text #14

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3700. Min Act: -0.0001

Data Index: 1396320 (Python Code)

Max Activating Token Index: 649

Text #15

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3576. Min Act: -0.0001

Data Index: 1626181 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3534. Min Act: -0.0001

Data Index: 1473057 (Python Code)

Max Activating Token Index: 497

Text #17

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3526. Min Act: -0.0001

Data Index: 1613817 (Python Code)

Max Activating Token Index: 113

Text #18

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3618. Min Act: -0.0001

Data Index: 1566481 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3505. Min Act: -0.0001

Data Index: 1526459 (Python Code)

Max Activating Token Index: 73