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

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

Neuron 4387 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4620. Min Act: -0.0002

Data Index: 1491840 (Python Code)

Max Activating Token Index: 620

Text #1

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4339. Min Act: -0.0002

Data Index: 1581787 (Python Code)

Max Activating Token Index: 200

Text #2

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3755. Min Act: -0.0002

Data Index: 1468503 (Python Code)

Max Activating Token Index: 512

Text #3

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4095. Min Act: -0.0002

Data Index: 1639039 (Python Code)

Max Activating Token Index: 629

Text #4

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.2820. Min Act: -0.0002

Data Index: 1535026 (Python Code)

Max Activating Token Index: 632

Text #5

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.5120. Min Act: -0.0002

Data Index: 384744 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3977. Min Act: -0.0002

Data Index: 1537616 (Python Code)

Max Activating Token Index: 365

Text #7

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3545. Min Act: -0.0002

Data Index: 1457342 (Python Code)

Max Activating Token Index: 753

Text #8

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3755. Min Act: -0.0002

Data Index: 1371409 (Python Code)

Max Activating Token Index: 490

Text #9

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3891. Min Act: -0.0002

Data Index: 1600828 (Python Code)

Max Activating Token Index: 369

Text #10

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3298. Min Act: -0.0002

Data Index: 1460631 (Python Code)

Max Activating Token Index: 421

Text #11

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4016. Min Act: -0.0002

Data Index: 1444231 (Python Code)

Max Activating Token Index: 162

Text #12

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3991. Min Act: -0.0002

Data Index: 1623287 (Python Code)

Max Activating Token Index: 625

Text #13

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4040. Min Act: -0.0002

Data Index: 1468245 (Python Code)

Max Activating Token Index: 121

Text #14

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3180. Min Act: -0.0002

Data Index: 1626673 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.2976. Min Act: -0.0002

Data Index: 1615255 (Python Code)

Max Activating Token Index: 766

Text #16

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4192. Min Act: -0.0002

Data Index: 1401504 (Python Code)

Max Activating Token Index: 893

Text #17

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3845. Min Act: -0.0002

Data Index: 1571146 (Python Code)

Max Activating Token Index: 836

Text #18

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4182. Min Act: -0.0002

Data Index: 1406058 (Python Code)

Max Activating Token Index: 380

Text #19

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.2719. Min Act: -0.0002

Data Index: 1482247 (Python Code)

Max Activating Token Index: 580