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

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

Neuron 1736 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: 2.2075. Min Range: -2.2075

Max Act: 2.0570. Min Act: -0.0000

Data Index: 1486447 (Python Code)

Max Activating Token Index: 36

Text #1

Max Range: 2.2075. Min Range: -2.2075

Max Act: 2.0597. Min Act: -0.0000

Data Index: 1507141 (Python Code)

Max Activating Token Index: 27

Text #2

Max Range: 2.2075. Min Range: -2.2075

Max Act: 2.1528. Min Act: -0.0001

Data Index: 1435217 (Python Code)

Max Activating Token Index: 587

Text #3

Max Range: 2.2075. Min Range: -2.2075

Max Act: 2.0384. Min Act: -0.0000

Data Index: 1566293 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.8799. Min Act: -0.0000

Data Index: 1603565 (Python Code)

Max Activating Token Index: 816

Text #5

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.8909. Min Act: -0.0000

Data Index: 1492607 (Python Code)

Max Activating Token Index: 336

Text #6

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.9195. Min Act: -0.0001

Data Index: 1394113 (Python Code)

Max Activating Token Index: 713

Text #7

Max Range: 2.2075. Min Range: -2.2075

Max Act: 2.2075. Min Act: -0.0000

Data Index: 1595750 (Python Code)

Max Activating Token Index: 685

Text #8

Max Range: 2.2075. Min Range: -2.2075

Max Act: 2.0984. Min Act: -0.0000

Data Index: 1523599 (Python Code)

Max Activating Token Index: 361

Text #9

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.8889. Min Act: -0.0000

Data Index: 1557153 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 2.2075. Min Range: -2.2075

Max Act: 2.0745. Min Act: -0.0000

Data Index: 1499700 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.9853. Min Act: -0.0001

Data Index: 1622397 (Python Code)

Max Activating Token Index: 968

Text #12

Max Range: 2.2075. Min Range: -2.2075

Max Act: 2.0817. Min Act: -0.0000

Data Index: 1589429 (Python Code)

Max Activating Token Index: 17

Text #13

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.8769. Min Act: -0.0000

Data Index: 1611094 (Python Code)

Max Activating Token Index: 960

Text #14

Max Range: 2.2075. Min Range: -2.2075

Max Act: 2.0729. Min Act: -0.0000

Data Index: 1458217 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 2.2075. Min Range: -2.2075

Max Act: 2.0791. Min Act: -0.0000

Data Index: 1389880 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.9707. Min Act: -0.0000

Data Index: 1481251 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 2.2075. Min Range: -2.2075

Max Act: 2.1604. Min Act: -0.0000

Data Index: 1461312 (Python Code)

Max Activating Token Index: 231

Text #18

Max Range: 2.2075. Min Range: -2.2075

Max Act: 2.0591. Min Act: -0.0001

Data Index: 1648608 (Python Code)

Max Activating Token Index: 50

Text #19

Max Range: 2.2075. Min Range: -2.2075

Max Act: 1.8544. Min Act: -0.0000

Data Index: 1490252 (Python Code)

Max Activating Token Index: 344