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

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

Neuron 1793 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.5917. Min Act: -0.0002

Data Index: 1459967 (Python Code)

Max Activating Token Index: 72

Text #1

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.2907. Min Act: -0.0002

Data Index: 1493644 (Python Code)

Max Activating Token Index: 635

Text #2

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.2518. Min Act: -0.0002

Data Index: 1581018 (Python Code)

Max Activating Token Index: 766

Text #3

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.2136. Min Act: -0.0002

Data Index: 1626116 (Python Code)

Max Activating Token Index: 321

Text #4

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1826. Min Act: -0.0002

Data Index: 1644182 (Python Code)

Max Activating Token Index: 459

Text #5

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1807. Min Act: -0.0002

Data Index: 1476635 (Python Code)

Max Activating Token Index: 946

Text #6

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1807. Min Act: -0.0002

Data Index: 1614105 (Python Code)

Max Activating Token Index: 792

Text #7

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1722. Min Act: -0.0002

Data Index: 1491128 (Python Code)

Max Activating Token Index: 430

Text #8

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1452. Min Act: -0.0002

Data Index: 1586274 (Python Code)

Max Activating Token Index: 901

Text #9

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1183. Min Act: -0.0002

Data Index: 1579466 (Python Code)

Max Activating Token Index: 838

Text #10

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1532. Min Act: -0.0002

Data Index: 1427949 (Python Code)

Max Activating Token Index: 364

Text #11

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1672. Min Act: -0.0002

Data Index: 1518336 (Python Code)

Max Activating Token Index: 191

Text #12

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1513. Min Act: -0.0002

Data Index: 1435971 (Python Code)

Max Activating Token Index: 552

Text #13

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1557. Min Act: -0.0002

Data Index: 1652134 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1338. Min Act: -0.0002

Data Index: 1410869 (Python Code)

Max Activating Token Index: 526

Text #15

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1440. Min Act: -0.0002

Data Index: 1524766 (Python Code)

Max Activating Token Index: 499

Text #16

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1178. Min Act: -0.0002

Data Index: 1410373 (Python Code)

Max Activating Token Index: 373

Text #17

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1364. Min Act: -0.0002

Data Index: 1508356 (Python Code)

Max Activating Token Index: 776

Text #18

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1323. Min Act: -0.0002

Data Index: 1413649 (Python Code)

Max Activating Token Index: 322

Text #19

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.0975. Min Act: -0.0002

Data Index: 1591949 (Python Code)

Max Activating Token Index: 900