Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 67 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.0052. Min Range: -8.0052

Max Act: 8.0052. Min Act: -0.1700

Data Index: 1644804 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 8.0052. Min Range: -8.0052

Max Act: 8.0052. Min Act: -0.1700

Data Index: 1376902 (Python Code)

Max Activating Token Index: 462

Text #2

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.8802. Min Act: -0.1700

Data Index: 1360541 (Python Code)

Max Activating Token Index: 977

Text #3

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.8802. Min Act: -0.1700

Data Index: 1570994 (Python Code)

Max Activating Token Index: 141

Text #4

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.8177. Min Act: -0.1700

Data Index: 1560074 (Python Code)

Max Activating Token Index: 628

Text #5

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.8177. Min Act: -0.1700

Data Index: 1570136 (Python Code)

Max Activating Token Index: 949

Text #6

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.8177. Min Act: -0.1700

Data Index: 1637087 (Python Code)

Max Activating Token Index: 367

Text #7

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.7240. Min Act: -0.1700

Data Index: 1468440 (Python Code)

Max Activating Token Index: 485

Text #8

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.7240. Min Act: -0.1700

Data Index: 1493468 (Python Code)

Max Activating Token Index: 978

Text #9

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.7240. Min Act: -0.1700

Data Index: 1381039 (Python Code)

Max Activating Token Index: 863

Text #10

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.7240. Min Act: -0.1700

Data Index: 1515872 (Python Code)

Max Activating Token Index: 700

Text #11

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.6927. Min Act: -0.1700

Data Index: 1585853 (Python Code)

Max Activating Token Index: 478

Text #12

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.6302. Min Act: -0.1700

Data Index: 1640126 (Python Code)

Max Activating Token Index: 739

Text #13

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.6302. Min Act: -0.1700

Data Index: 1650596 (Python Code)

Max Activating Token Index: 338

Text #14

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.6615. Min Act: -0.1700

Data Index: 1427805 (Python Code)

Max Activating Token Index: 735

Text #15

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.6927. Min Act: -0.1700

Data Index: 1639361 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.6615. Min Act: -0.1700

Data Index: 1519066 (Python Code)

Max Activating Token Index: 26

Text #17

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.6615. Min Act: -0.1700

Data Index: 1568455 (Python Code)

Max Activating Token Index: 532

Text #18

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.6302. Min Act: -0.1700

Data Index: 1429125 (Python Code)

Max Activating Token Index: 663

Text #19

Max Range: 8.0052. Min Range: -8.0052

Max Act: 7.7240. Min Act: -0.1700

Data Index: 1410190 (Python Code)

Max Activating Token Index: 183