Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1239 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.2637. Min Act: -0.1700

Data Index: 1458125 (Python Code)

Max Activating Token Index: 987

Text #1

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.2158. Min Act: -0.0995

Data Index: 1619078 (Python Code)

Max Activating Token Index: 627

Text #2

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.1540. Min Act: -0.1699

Data Index: 1427541 (Python Code)

Max Activating Token Index: 383

Text #3

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.1364. Min Act: -0.1699

Data Index: 1594685 (Python Code)

Max Activating Token Index: 304

Text #4

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.0955. Min Act: -0.1224

Data Index: 1374851 (Python Code)

Max Activating Token Index: 889

Text #5

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.1052. Min Act: -0.1699

Data Index: 1434862 (Python Code)

Max Activating Token Index: 238

Text #6

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.0929. Min Act: -0.1700

Data Index: 1634775 (Python Code)

Max Activating Token Index: 973

Text #7

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.0718. Min Act: -0.0995

Data Index: 1603753 (Python Code)

Max Activating Token Index: 809

Text #8

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.0545. Min Act: -0.1700

Data Index: 1475358 (Python Code)

Max Activating Token Index: 167

Text #9

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.0708. Min Act: -0.0995

Data Index: 1412809 (Python Code)

Max Activating Token Index: 192

Text #10

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.0236. Min Act: -0.1698

Data Index: 1652318 (Python Code)

Max Activating Token Index: 563

Text #11

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.0284. Min Act: -0.1700

Data Index: 1457243 (Python Code)

Max Activating Token Index: 968

Text #12

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.0228. Min Act: -0.1688

Data Index: 1413204 (Python Code)

Max Activating Token Index: 213

Text #13

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.0500. Min Act: -0.1696

Data Index: 1543383 (Python Code)

Max Activating Token Index: 569

Text #14

Max Range: 3.2637. Min Range: -3.2637

Max Act: 2.9891. Min Act: -0.1699

Data Index: 1594192 (Python Code)

Max Activating Token Index: 704

Text #15

Max Range: 3.2637. Min Range: -3.2637

Max Act: 2.9836. Min Act: -0.1694

Data Index: 1371534 (Python Code)

Max Activating Token Index: 281

Text #16

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.0052. Min Act: -0.1699

Data Index: 1432482 (Python Code)

Max Activating Token Index: 865

Text #17

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.0054. Min Act: -0.1699

Data Index: 1375930 (Python Code)

Max Activating Token Index: 607

Text #18

Max Range: 3.2637. Min Range: -3.2637

Max Act: 3.0006. Min Act: -0.1697

Data Index: 1575021 (Python Code)

Max Activating Token Index: 165

Text #19

Max Range: 3.2637. Min Range: -3.2637

Max Act: 2.9667. Min Act: -0.1700

Data Index: 1565036 (Python Code)

Max Activating Token Index: 695