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

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

Neuron 626 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4113. Min Range: -6.4113

Max Act: 6.4113. Min Act: -0.0000

Data Index: 1478143 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 6.4113. Min Range: -6.4113

Max Act: 6.4097. Min Act: -0.0000

Data Index: 1557487 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 6.4113. Min Range: -6.4113

Max Act: 6.3210. Min Act: -0.0000

Data Index: 1388927 (Python Code)

Max Activating Token Index: 632

Text #3

Max Range: 6.4113. Min Range: -6.4113

Max Act: 6.2983. Min Act: -0.0000

Data Index: 1457397 (Python Code)

Max Activating Token Index: 63

Text #4

Max Range: 6.4113. Min Range: -6.4113

Max Act: 6.1093. Min Act: -0.0000

Data Index: 1565800 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 6.4113. Min Range: -6.4113

Max Act: 6.3950. Min Act: -0.0000

Data Index: 1647495 (Python Code)

Max Activating Token Index: 24

Text #6

Max Range: 6.4113. Min Range: -6.4113

Max Act: 6.1784. Min Act: -0.0000

Data Index: 1359981 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 6.4113. Min Range: -6.4113

Max Act: 6.0566. Min Act: -0.0000

Data Index: 1431917 (Python Code)

Max Activating Token Index: 45

Text #8

Max Range: 6.4113. Min Range: -6.4113

Max Act: 6.0340. Min Act: -0.0000

Data Index: 1608087 (Python Code)

Max Activating Token Index: 30

Text #9

Max Range: 6.4113. Min Range: -6.4113

Max Act: 5.8415. Min Act: -0.0000

Data Index: 1523095 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 6.4113. Min Range: -6.4113

Max Act: 5.6399. Min Act: -0.0000

Data Index: 1480664 (Python Code)

Max Activating Token Index: 381

Text #11

Max Range: 6.4113. Min Range: -6.4113

Max Act: 5.9915. Min Act: -0.0000

Data Index: 1533543 (Python Code)

Max Activating Token Index: 22

Text #12

Max Range: 6.4113. Min Range: -6.4113

Max Act: 5.9807. Min Act: -0.0000

Data Index: 1420294 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 6.4113. Min Range: -6.4113

Max Act: 6.1418. Min Act: -0.0000

Data Index: 1368432 (Python Code)

Max Activating Token Index: 550

Text #14

Max Range: 6.4113. Min Range: -6.4113

Max Act: 5.7739. Min Act: -0.0000

Data Index: 1590917 (Python Code)

Max Activating Token Index: 18

Text #15

Max Range: 6.4113. Min Range: -6.4113

Max Act: 5.6863. Min Act: -0.0000

Data Index: 1445564 (Python Code)

Max Activating Token Index: 933

Text #16

Max Range: 6.4113. Min Range: -6.4113

Max Act: 5.8525. Min Act: -0.0000

Data Index: 1500740 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 6.4113. Min Range: -6.4113

Max Act: 5.8245. Min Act: -0.0000

Data Index: 1378544 (Python Code)

Max Activating Token Index: 370

Text #18

Max Range: 6.4113. Min Range: -6.4113

Max Act: 5.6530. Min Act: -0.0000

Data Index: 1532765 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 6.4113. Min Range: -6.4113

Max Act: 5.6454. Min Act: -0.0000

Data Index: 1527644 (Python Code)

Max Activating Token Index: 14