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

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

Neuron 987 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: 3.1283. Min Range: -3.1283

Max Act: 3.1283. Min Act: -0.1700

Data Index: 1448896 (Python Code)

Max Activating Token Index: 479

Text #1

Max Range: 3.1283. Min Range: -3.1283

Max Act: 3.1200. Min Act: -0.1700

Data Index: 1489372 (Python Code)

Max Activating Token Index: 647

Text #2

Max Range: 3.1283. Min Range: -3.1283

Max Act: 3.1111. Min Act: -0.1700

Data Index: 1473731 (Python Code)

Max Activating Token Index: 1012

Text #3

Max Range: 3.1283. Min Range: -3.1283

Max Act: 3.0254. Min Act: -0.1700

Data Index: 1506599 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 3.1283. Min Range: -3.1283

Max Act: 3.0355. Min Act: -0.1700

Data Index: 1397135 (Python Code)

Max Activating Token Index: 981

Text #5

Max Range: 3.1283. Min Range: -3.1283

Max Act: 3.0419. Min Act: -0.1700

Data Index: 1413733 (Python Code)

Max Activating Token Index: 379

Text #6

Max Range: 3.1283. Min Range: -3.1283

Max Act: 3.0271. Min Act: -0.1700

Data Index: 1576773 (Python Code)

Max Activating Token Index: 758

Text #7

Max Range: 3.1283. Min Range: -3.1283

Max Act: 3.0208. Min Act: -0.1700

Data Index: 1485992 (Python Code)

Max Activating Token Index: 310

Text #8

Max Range: 3.1283. Min Range: -3.1283

Max Act: 3.0133. Min Act: -0.1700

Data Index: 1450019 (Python Code)

Max Activating Token Index: 515

Text #9

Max Range: 3.1283. Min Range: -3.1283

Max Act: 2.9718. Min Act: -0.1700

Data Index: 956448 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 3.1283. Min Range: -3.1283

Max Act: 2.9699. Min Act: -0.1700

Data Index: 841190 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 3.1283. Min Range: -3.1283

Max Act: 2.9590. Min Act: -0.1700

Data Index: 1617743 (Python Code)

Max Activating Token Index: 645

Text #12

Max Range: 3.1283. Min Range: -3.1283

Max Act: 2.9305. Min Act: -0.1700

Data Index: 1459519 (Python Code)

Max Activating Token Index: 651

Text #13

Max Range: 3.1283. Min Range: -3.1283

Max Act: 2.9243. Min Act: -0.1700

Data Index: 391041 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 3.1283. Min Range: -3.1283

Max Act: 2.9095. Min Act: -0.1700

Data Index: 1465501 (Python Code)

Max Activating Token Index: 704

Text #15

Max Range: 3.1283. Min Range: -3.1283

Max Act: 2.9163. Min Act: -0.1700

Data Index: 1636930 (Python Code)

Max Activating Token Index: 845

Text #16

Max Range: 3.1283. Min Range: -3.1283

Max Act: 2.9119. Min Act: -0.1700

Data Index: 1548035 (Python Code)

Max Activating Token Index: 854

Text #17

Max Range: 3.1283. Min Range: -3.1283

Max Act: 2.9061. Min Act: -0.1700

Data Index: 1487665 (Python Code)

Max Activating Token Index: 206

Text #18

Max Range: 3.1283. Min Range: -3.1283

Max Act: 2.8873. Min Act: -0.1700

Data Index: 1552687 (Python Code)

Max Activating Token Index: 462

Text #19

Max Range: 3.1283. Min Range: -3.1283

Max Act: 2.8771. Min Act: -0.1700

Data Index: 1469570 (Python Code)

Max Activating Token Index: 370