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

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

Neuron 1145 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: 1.3920. Min Range: -1.3920

Max Act: 1.3660. Min Act: -0.0000

Data Index: 1568737 (Python Code)

Max Activating Token Index: 656

Text #1

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.3920. Min Act: -0.0000

Data Index: 1637264 (Python Code)

Max Activating Token Index: 413

Text #2

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.1075. Min Act: -0.0000

Data Index: 738134 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.1185. Min Act: -0.0000

Data Index: 1456883 (Python Code)

Max Activating Token Index: 465

Text #4

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.0833. Min Act: -0.0000

Data Index: 1469543 (Python Code)

Max Activating Token Index: 381

Text #5

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1421731 (Python Code)

Max Activating Token Index: 221

Text #6

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1427314 (Python Code)

Max Activating Token Index: 283

Text #7

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1549806 (Python Code)

Max Activating Token Index: 334

Text #8

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1412107 (Python Code)

Max Activating Token Index: 529

Text #9

Max Range: 1.3920. Min Range: -1.3920

Max Act: 1.0205. Min Act: -0.0000

Data Index: 1596852 (Python Code)

Max Activating Token Index: 614

Text #10

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1651472 (Python Code)

Max Activating Token Index: 884

Text #11

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1563490 (Python Code)

Max Activating Token Index: 421

Text #12

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1446018 (Python Code)

Max Activating Token Index: 559

Text #13

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.8587. Min Act: -0.0000

Data Index: 1467670 (Python Code)

Max Activating Token Index: 394

Text #14

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.8004. Min Act: -0.0000

Data Index: 1648746 (Python Code)

Max Activating Token Index: 520

Text #15

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1419315 (Python Code)

Max Activating Token Index: 851

Text #16

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.8031. Min Act: -0.0000

Data Index: 246949 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.8191. Min Act: -0.0000

Data Index: 1426233 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1466860 (Python Code)

Max Activating Token Index: 994

Text #19

Max Range: 1.3920. Min Range: -1.3920

Max Act: 0.7985. Min Act: -0.0000

Data Index: 1471313 (Python Code)

Max Activating Token Index: 974