Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1215 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0657. Min Act: -0.0006

Data Index: 1649018 (Python Code)

Max Activating Token Index: 624

Text #1

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0435. Min Act: -0.0006

Data Index: 1620118 (Python Code)

Max Activating Token Index: 286

Text #2

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0474. Min Act: -0.0006

Data Index: 1384590 (Python Code)

Max Activating Token Index: 255

Text #3

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0451. Min Act: -0.0006

Data Index: 1516398 (Python Code)

Max Activating Token Index: 71

Text #4

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0482. Min Act: -0.0006

Data Index: 1633248 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0438. Min Act: -0.0006

Data Index: 1496253 (Python Code)

Max Activating Token Index: 583

Text #6

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0462. Min Act: -0.0006

Data Index: 1494656 (Python Code)

Max Activating Token Index: 206

Text #7

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0471. Min Act: -0.0006

Data Index: 1534252 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0440. Min Act: -0.0006

Data Index: 1504107 (Python Code)

Max Activating Token Index: 228

Text #9

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0418. Min Act: -0.0005

Data Index: 1633421 (Python Code)

Max Activating Token Index: 739

Text #10

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0465. Min Act: -0.0006

Data Index: 1652634 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0392. Min Act: -0.0006

Data Index: 1512363 (Python Code)

Max Activating Token Index: 234

Text #12

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0430. Min Act: -0.0006

Data Index: 1434855 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0400. Min Act: -0.0006

Data Index: 1543852 (Python Code)

Max Activating Token Index: 568

Text #14

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0422. Min Act: -0.0006

Data Index: 1495288 (Python Code)

Max Activating Token Index: 247

Text #15

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0348. Min Act: -0.0006

Data Index: 1421276 (Python Code)

Max Activating Token Index: 654

Text #16

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0438. Min Act: -0.0006

Data Index: 1615917 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0377. Min Act: -0.0006

Data Index: 1645882 (Python Code)

Max Activating Token Index: 693

Text #18

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0378. Min Act: -0.0006

Data Index: 1636730 (Python Code)

Max Activating Token Index: 304

Text #19

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0415. Min Act: -0.0006

Data Index: 1492042 (Python Code)

Max Activating Token Index: 729