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

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

Neuron 1927 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.5505. Min Act: -0.0000

Data Index: 1440303 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1412628 (Python Code)

Max Activating Token Index: 358

Text #2

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1362697 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1546794 (Python Code)

Max Activating Token Index: 623

Text #4

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1425168 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1633899 (Python Code)

Max Activating Token Index: 94

Text #6

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1598696 (Python Code)

Max Activating Token Index: 430

Text #7

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1655462 (Python Code)

Max Activating Token Index: 180

Text #8

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1656475 (Python Code)

Max Activating Token Index: 265

Text #9

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.5272. Min Act: -0.0000

Data Index: 1593400 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1559358 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1395401 (Python Code)

Max Activating Token Index: 417

Text #12

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.5253. Min Act: 0.0000

Data Index: 1611024 (Python Code)

Max Activating Token Index: 121

Text #13

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1462671 (Python Code)

Max Activating Token Index: 367

Text #14

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1426757 (Python Code)

Max Activating Token Index: 127

Text #15

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1365319 (Python Code)

Max Activating Token Index: 1005

Text #16

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1648321 (Python Code)

Max Activating Token Index: 832

Text #17

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1391705 (Python Code)

Max Activating Token Index: 47

Text #18

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1412375 (Python Code)

Max Activating Token Index: 401

Text #19

Max Range: 0.6784. Min Range: -0.6784

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1539848 (Python Code)

Max Activating Token Index: 285