Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1316 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.5981. Min Range: -5.5981

Max Act: 5.3410. Min Act: -0.0001

Data Index: 1393174 (Python Code)

Max Activating Token Index: 895

Text #1

Max Range: 5.5981. Min Range: -5.5981

Max Act: 5.5791. Min Act: -0.0001

Data Index: 1611072 (Python Code)

Max Activating Token Index: 915

Text #2

Max Range: 5.5981. Min Range: -5.5981

Max Act: 5.5082. Min Act: -0.0001

Data Index: 1622823 (Python Code)

Max Activating Token Index: 902

Text #3

Max Range: 5.5981. Min Range: -5.5981

Max Act: 5.2728. Min Act: -0.0000

Data Index: 1523351 (Python Code)

Max Activating Token Index: 941

Text #4

Max Range: 5.5981. Min Range: -5.5981

Max Act: 5.0534. Min Act: -0.0001

Data Index: 1597459 (Python Code)

Max Activating Token Index: 858

Text #5

Max Range: 5.5981. Min Range: -5.5981

Max Act: 4.8651. Min Act: -0.0001

Data Index: 1584291 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 5.5981. Min Range: -5.5981

Max Act: 5.5787. Min Act: -0.0001

Data Index: 1491714 (Python Code)

Max Activating Token Index: 949

Text #7

Max Range: 5.5981. Min Range: -5.5981

Max Act: 5.5454. Min Act: -0.0001

Data Index: 1487528 (Python Code)

Max Activating Token Index: 723

Text #8

Max Range: 5.5981. Min Range: -5.5981

Max Act: 4.8597. Min Act: -0.0000

Data Index: 1465054 (Python Code)

Max Activating Token Index: 967

Text #9

Max Range: 5.5981. Min Range: -5.5981

Max Act: 4.3438. Min Act: -0.0001

Data Index: 1489852 (Python Code)

Max Activating Token Index: 760

Text #10

Max Range: 5.5981. Min Range: -5.5981

Max Act: 5.0292. Min Act: -0.0001

Data Index: 1651015 (Python Code)

Max Activating Token Index: 994

Text #11

Max Range: 5.5981. Min Range: -5.5981

Max Act: 4.8492. Min Act: -0.0001

Data Index: 1409813 (Python Code)

Max Activating Token Index: 715

Text #12

Max Range: 5.5981. Min Range: -5.5981

Max Act: 4.8136. Min Act: -0.0001

Data Index: 1399373 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 5.5981. Min Range: -5.5981

Max Act: 4.4517. Min Act: -0.0001

Data Index: 1572116 (Python Code)

Max Activating Token Index: 116

Text #14

Max Range: 5.5981. Min Range: -5.5981

Max Act: 5.4903. Min Act: -0.0001

Data Index: 1538066 (Python Code)

Max Activating Token Index: 306

Text #15

Max Range: 5.5981. Min Range: -5.5981

Max Act: 5.0954. Min Act: -0.0001

Data Index: 1508133 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 5.5981. Min Range: -5.5981

Max Act: 5.5981. Min Act: -0.0000

Data Index: 1501358 (Python Code)

Max Activating Token Index: 821

Text #17

Max Range: 5.5981. Min Range: -5.5981

Max Act: 4.7570. Min Act: -0.0001

Data Index: 1490484 (Python Code)

Max Activating Token Index: 826

Text #18

Max Range: 5.5981. Min Range: -5.5981

Max Act: 4.9039. Min Act: -0.0001

Data Index: 1426467 (Python Code)

Max Activating Token Index: 841

Text #19

Max Range: 5.5981. Min Range: -5.5981

Max Act: 4.9249. Min Act: -0.0001

Data Index: 1632541 (Python Code)

Max Activating Token Index: 844