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

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

Neuron 4513 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: 2.8946. Min Range: -2.8946

Max Act: 2.8946. Min Act: -0.0000

Data Index: 1385403 (Python Code)

Max Activating Token Index: 482

Text #1

Max Range: 2.8946. Min Range: -2.8946

Max Act: 2.4773. Min Act: -0.0000

Data Index: 1568239 (Python Code)

Max Activating Token Index: 204

Text #2

Max Range: 2.8946. Min Range: -2.8946

Max Act: 2.5188. Min Act: -0.0000

Data Index: 1597158 (Python Code)

Max Activating Token Index: 334

Text #3

Max Range: 2.8946. Min Range: -2.8946

Max Act: 2.2146. Min Act: -0.0000

Data Index: 1362566 (Python Code)

Max Activating Token Index: 325

Text #4

Max Range: 2.8946. Min Range: -2.8946

Max Act: 2.1867. Min Act: -0.0000

Data Index: 1645538 (Python Code)

Max Activating Token Index: 188

Text #5

Max Range: 2.8946. Min Range: -2.8946

Max Act: 2.2641. Min Act: -0.0000

Data Index: 1513459 (Python Code)

Max Activating Token Index: 655

Text #6

Max Range: 2.8946. Min Range: -2.8946

Max Act: 2.2621. Min Act: -0.0000

Data Index: 1492825 (Python Code)

Max Activating Token Index: 52

Text #7

Max Range: 2.8946. Min Range: -2.8946

Max Act: 2.1265. Min Act: -0.0000

Data Index: 1394028 (Python Code)

Max Activating Token Index: 589

Text #8

Max Range: 2.8946. Min Range: -2.8946

Max Act: 2.1826. Min Act: -0.0000

Data Index: 1480910 (Python Code)

Max Activating Token Index: 764

Text #9

Max Range: 2.8946. Min Range: -2.8946

Max Act: 1.9109. Min Act: -0.0000

Data Index: 1585266 (Python Code)

Max Activating Token Index: 492

Text #10

Max Range: 2.8946. Min Range: -2.8946

Max Act: 1.9998. Min Act: -0.0000

Data Index: 1368534 (Python Code)

Max Activating Token Index: 379

Text #11

Max Range: 2.8946. Min Range: -2.8946

Max Act: 1.9751. Min Act: -0.0000

Data Index: 1588379 (Python Code)

Max Activating Token Index: 401

Text #12

Max Range: 2.8946. Min Range: -2.8946

Max Act: 1.9473. Min Act: -0.0000

Data Index: 1466151 (Python Code)

Max Activating Token Index: 332

Text #13

Max Range: 2.8946. Min Range: -2.8946

Max Act: 2.2624. Min Act: -0.0000

Data Index: 1580248 (Python Code)

Max Activating Token Index: 259

Text #14

Max Range: 2.8946. Min Range: -2.8946

Max Act: 1.8108. Min Act: -0.0000

Data Index: 1623884 (Python Code)

Max Activating Token Index: 813

Text #15

Max Range: 2.8946. Min Range: -2.8946

Max Act: 1.7516. Min Act: -0.0000

Data Index: 1382883 (Python Code)

Max Activating Token Index: 265

Text #16

Max Range: 2.8946. Min Range: -2.8946

Max Act: 1.8471. Min Act: -0.0000

Data Index: 1504819 (Python Code)

Max Activating Token Index: 873

Text #17

Max Range: 2.8946. Min Range: -2.8946

Max Act: 1.6500. Min Act: -0.0000

Data Index: 1532732 (Python Code)

Max Activating Token Index: 78

Text #18

Max Range: 2.8946. Min Range: -2.8946

Max Act: 1.8224. Min Act: -0.0000

Data Index: 1462383 (Python Code)

Max Activating Token Index: 435

Text #19

Max Range: 2.8946. Min Range: -2.8946

Max Act: 1.8076. Min Act: -0.0000

Data Index: 1653737 (Python Code)

Max Activating Token Index: 678