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

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

Neuron 1568 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: 3.5447. Min Range: -3.5447

Max Act: 3.5447. Min Act: -0.1700

Data Index: 1430712 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.4826. Min Act: -0.1700

Data Index: 1638730 (Python Code)

Max Activating Token Index: 617

Text #2

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.4088. Min Act: -0.1700

Data Index: 1388224 (Python Code)

Max Activating Token Index: 954

Text #3

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.3953. Min Act: -0.1700

Data Index: 1359932 (Python Code)

Max Activating Token Index: 1006

Text #4

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.3898. Min Act: -0.1700

Data Index: 1587528 (Python Code)

Max Activating Token Index: 311

Text #5

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.3875. Min Act: -0.1700

Data Index: 1609686 (Python Code)

Max Activating Token Index: 423

Text #6

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.3786. Min Act: -0.1700

Data Index: 1424150 (Python Code)

Max Activating Token Index: 511

Text #7

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.3659. Min Act: -0.1700

Data Index: 1481439 (Python Code)

Max Activating Token Index: 61

Text #8

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.3562. Min Act: -0.1700

Data Index: 1393338 (Python Code)

Max Activating Token Index: 918

Text #9

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.3212. Min Act: -0.1700

Data Index: 1491079 (Python Code)

Max Activating Token Index: 662

Text #10

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.2914. Min Act: -0.1700

Data Index: 1458415 (Python Code)

Max Activating Token Index: 183

Text #11

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.2922. Min Act: -0.1700

Data Index: 1459004 (Python Code)

Max Activating Token Index: 943

Text #12

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.2868. Min Act: -0.1700

Data Index: 819292 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.2953. Min Act: -0.1700

Data Index: 1367774 (Python Code)

Max Activating Token Index: 795

Text #14

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.2796. Min Act: -0.1700

Data Index: 1445207 (Python Code)

Max Activating Token Index: 591

Text #15

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.2507. Min Act: -0.1700

Data Index: 1497016 (Python Code)

Max Activating Token Index: 995

Text #16

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.2531. Min Act: -0.1700

Data Index: 1420365 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.2430. Min Act: -0.1700

Data Index: 1503611 (Python Code)

Max Activating Token Index: 836

Text #18

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.2400. Min Act: -0.1700

Data Index: 1489223 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 3.5447. Min Range: -3.5447

Max Act: 3.2404. Min Act: -0.1700

Data Index: 1507951 (Python Code)

Max Activating Token Index: 25