Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5909 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4016. Min Range: -2.4016

Max Act: 2.4016. Min Act: -0.0000

Data Index: 1471143 (Python Code)

Max Activating Token Index: 284

Text #1

Max Range: 2.4016. Min Range: -2.4016

Max Act: 2.3344. Min Act: -0.0000

Data Index: 1487903 (Python Code)

Max Activating Token Index: 329

Text #2

Max Range: 2.4016. Min Range: -2.4016

Max Act: 2.0769. Min Act: -0.0000

Data Index: 1495915 (Python Code)

Max Activating Token Index: 209

Text #3

Max Range: 2.4016. Min Range: -2.4016

Max Act: 2.1650. Min Act: -0.0000

Data Index: 1505799 (Python Code)

Max Activating Token Index: 127

Text #4

Max Range: 2.4016. Min Range: -2.4016

Max Act: 2.0036. Min Act: -0.0000

Data Index: 1463114 (Python Code)

Max Activating Token Index: 261

Text #5

Max Range: 2.4016. Min Range: -2.4016

Max Act: 2.0099. Min Act: -0.0000

Data Index: 1449216 (Python Code)

Max Activating Token Index: 209

Text #6

Max Range: 2.4016. Min Range: -2.4016

Max Act: 2.0181. Min Act: -0.0000

Data Index: 1512443 (Python Code)

Max Activating Token Index: 431

Text #7

Max Range: 2.4016. Min Range: -2.4016

Max Act: 1.9538. Min Act: -0.0000

Data Index: 1629081 (Python Code)

Max Activating Token Index: 144

Text #8

Max Range: 2.4016. Min Range: -2.4016

Max Act: 1.9734. Min Act: -0.0000

Data Index: 1507616 (Python Code)

Max Activating Token Index: 114

Text #9

Max Range: 2.4016. Min Range: -2.4016

Max Act: 1.9555. Min Act: -0.0000

Data Index: 1522667 (Python Code)

Max Activating Token Index: 334

Text #10

Max Range: 2.4016. Min Range: -2.4016

Max Act: 1.8477. Min Act: -0.0000

Data Index: 1409175 (Python Code)

Max Activating Token Index: 342

Text #11

Max Range: 2.4016. Min Range: -2.4016

Max Act: 1.9261. Min Act: -0.0000

Data Index: 1413180 (Python Code)

Max Activating Token Index: 314

Text #12

Max Range: 2.4016. Min Range: -2.4016

Max Act: 1.9247. Min Act: -0.0000

Data Index: 1460794 (Python Code)

Max Activating Token Index: 1008

Text #13

Max Range: 2.4016. Min Range: -2.4016

Max Act: 1.9005. Min Act: -0.0000

Data Index: 1513671 (Python Code)

Max Activating Token Index: 850

Text #14

Max Range: 2.4016. Min Range: -2.4016

Max Act: 1.9341. Min Act: -0.0000

Data Index: 1529418 (Python Code)

Max Activating Token Index: 117

Text #15

Max Range: 2.4016. Min Range: -2.4016

Max Act: 1.8248. Min Act: -0.0000

Data Index: 1614057 (Python Code)

Max Activating Token Index: 246

Text #16

Max Range: 2.4016. Min Range: -2.4016

Max Act: 1.8606. Min Act: -0.0000

Data Index: 1395016 (Python Code)

Max Activating Token Index: 117

Text #17

Max Range: 2.4016. Min Range: -2.4016

Max Act: 1.8568. Min Act: -0.0000

Data Index: 1392372 (Python Code)

Max Activating Token Index: 111

Text #18

Max Range: 2.4016. Min Range: -2.4016

Max Act: 1.8537. Min Act: -0.0000

Data Index: 1498293 (Python Code)

Max Activating Token Index: 164

Text #19

Max Range: 2.4016. Min Range: -2.4016

Max Act: 1.9020. Min Act: -0.0000

Data Index: 1543212 (Python Code)

Max Activating Token Index: 482