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

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

Neuron 4030 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: 1.4390. Min Range: -1.4390

Max Act: 1.4390. Min Act: -0.0000

Data Index: 1043315 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1357085 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1584682 (Python Code)

Max Activating Token Index: 369

Text #3

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1391095 (Python Code)

Max Activating Token Index: 733

Text #4

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.4184. Min Act: -0.0000

Data Index: 675139 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1646303 (Python Code)

Max Activating Token Index: 1013

Text #6

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1385956 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1516647 (Python Code)

Max Activating Token Index: 353

Text #8

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1549483 (Python Code)

Max Activating Token Index: 169

Text #9

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1486488 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1374872 (Python Code)

Max Activating Token Index: 357

Text #11

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1209520 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1379266 (Python Code)

Max Activating Token Index: 661

Text #13

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3688. Min Act: -0.0000

Data Index: 1517420 (Python Code)

Max Activating Token Index: 858

Text #14

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1560938 (Python Code)

Max Activating Token Index: 650

Text #15

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1651313 (Python Code)

Max Activating Token Index: 83

Text #16

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1553764 (Python Code)

Max Activating Token Index: 322

Text #17

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1512904 (Python Code)

Max Activating Token Index: 800

Text #18

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1568485 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1439875 (Python Code)

Max Activating Token Index: 407