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

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

Neuron 1242 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1558443 (Python Code)

Max Activating Token Index: 825

Text #1

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1591971 (Python Code)

Max Activating Token Index: 741

Text #2

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1414583 (Python Code)

Max Activating Token Index: 551

Text #3

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1464591 (Python Code)

Max Activating Token Index: 63

Text #4

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1568536 (Python Code)

Max Activating Token Index: 211

Text #5

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4867. Min Act: -0.0000

Data Index: 1586209 (Python Code)

Max Activating Token Index: 149

Text #6

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1532485 (Python Code)

Max Activating Token Index: 440

Text #7

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1532057 (Python Code)

Max Activating Token Index: 306

Text #8

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1500872 (Python Code)

Max Activating Token Index: 257

Text #9

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1641739 (Python Code)

Max Activating Token Index: 376

Text #10

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4675. Min Act: -0.0000

Data Index: 1437579 (Python Code)

Max Activating Token Index: 167

Text #11

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1571230 (Python Code)

Max Activating Token Index: 200

Text #12

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4724. Min Act: -0.0000

Data Index: 1538543 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1437017 (Python Code)

Max Activating Token Index: 27

Text #14

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1503124 (Python Code)

Max Activating Token Index: 688

Text #15

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1555647 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1532979 (Python Code)

Max Activating Token Index: 285

Text #17

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1584183 (Python Code)

Max Activating Token Index: 675

Text #18

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1529294 (Python Code)

Max Activating Token Index: 486

Text #19

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1529903 (Python Code)

Max Activating Token Index: 22