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

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

Neuron 5024 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: 1.4618. Min Range: -1.4618

Max Act: 1.4618. Min Act: -0.0000

Data Index: 1609330 (Python Code)

Max Activating Token Index: 337

Text #1

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.3727. Min Act: -0.0000

Data Index: 1510508 (Python Code)

Max Activating Token Index: 84

Text #2

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.3335. Min Act: -0.0001

Data Index: 1101008 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1402182 (Python Code)

Max Activating Token Index: 147

Text #4

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.1220. Min Act: -0.0001

Data Index: 210738 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0605. Min Act: -0.0001

Data Index: 1585743 (Python Code)

Max Activating Token Index: 645

Text #6

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.1496. Min Act: -0.0001

Data Index: 1572168 (Python Code)

Max Activating Token Index: 111

Text #7

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.1431. Min Act: -0.0000

Data Index: 1010136 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.1069. Min Act: -0.0000

Data Index: 1370430 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0420. Min Act: -0.0001

Data Index: 158567 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0071. Min Act: -0.0001

Data Index: 1589116 (Python Code)

Max Activating Token Index: 144

Text #11

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.9988. Min Act: -0.0001

Data Index: 1590133 (Python Code)

Max Activating Token Index: 357

Text #12

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0913. Min Act: -0.0001

Data Index: 921460 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0400. Min Act: -0.0001

Data Index: 1494913 (Python Code)

Max Activating Token Index: 70

Text #14

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.9778. Min Act: -0.0001

Data Index: 1435422 (Python Code)

Max Activating Token Index: 107

Text #15

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1458217 (Python Code)

Max Activating Token Index: 632

Text #16

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.9672. Min Act: -0.0001

Data Index: 1633892 (Python Code)

Max Activating Token Index: 133

Text #17

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1496537 (Python Code)

Max Activating Token Index: 966

Text #18

Max Range: 1.4618. Min Range: -1.4618

Max Act: 1.0013. Min Act: -0.0000

Data Index: 1468746 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 1.4618. Min Range: -1.4618

Max Act: 0.9681. Min Act: -0.0000

Data Index: 1360468 (Python Code)

Max Activating Token Index: 82