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

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

Neuron 359 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: 3.1346. Min Range: -3.1346

Max Act: 3.1241. Min Act: -0.1700

Data Index: 1454371 (Python Code)

Max Activating Token Index: 738

Text #1

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.1346. Min Act: -0.1700

Data Index: 1580453 (Python Code)

Max Activating Token Index: 1020

Text #2

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.1208. Min Act: -0.1700

Data Index: 1650886 (Python Code)

Max Activating Token Index: 188

Text #3

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0283. Min Act: -0.1700

Data Index: 1391609 (Python Code)

Max Activating Token Index: 862

Text #4

Max Range: 3.1346. Min Range: -3.1346

Max Act: 3.0197. Min Act: -0.1700

Data Index: 1581879 (Python Code)

Max Activating Token Index: 352

Text #5

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.9966. Min Act: -0.1700

Data Index: 1654113 (Python Code)

Max Activating Token Index: 106

Text #6

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.9824. Min Act: -0.1700

Data Index: 1606496 (Python Code)

Max Activating Token Index: 414

Text #7

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.9640. Min Act: -0.1700

Data Index: 1466275 (Python Code)

Max Activating Token Index: 354

Text #8

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.9209. Min Act: -0.1700

Data Index: 1448759 (Python Code)

Max Activating Token Index: 277

Text #9

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.9448. Min Act: -0.1700

Data Index: 1608697 (Python Code)

Max Activating Token Index: 559

Text #10

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.9293. Min Act: -0.1700

Data Index: 1393584 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.9345. Min Act: -0.1700

Data Index: 1555099 (Python Code)

Max Activating Token Index: 568

Text #12

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.9187. Min Act: -0.1700

Data Index: 1402794 (Python Code)

Max Activating Token Index: 697

Text #13

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.8960. Min Act: -0.1700

Data Index: 1508081 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.9077. Min Act: -0.1700

Data Index: 1468906 (Python Code)

Max Activating Token Index: 681

Text #15

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.8697. Min Act: -0.1700

Data Index: 1446833 (Python Code)

Max Activating Token Index: 835

Text #16

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.8767. Min Act: -0.1700

Data Index: 1597969 (Python Code)

Max Activating Token Index: 277

Text #17

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.8634. Min Act: -0.1700

Data Index: 146218 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.8580. Min Act: -0.1700

Data Index: 1584117 (Python Code)

Max Activating Token Index: 867

Text #19

Max Range: 3.1346. Min Range: -3.1346

Max Act: 2.8574. Min Act: -0.1700

Data Index: 1650646 (Python Code)

Max Activating Token Index: 995