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

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

Neuron 527 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: 3.2332. Min Range: -3.2332

Max Act: 3.2332. Min Act: -0.1700

Data Index: 1378147 (Python Code)

Max Activating Token Index: 279

Text #1

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.2102. Min Act: -0.1700

Data Index: 374557 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.1816. Min Act: -0.1700

Data Index: 270986 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.1900. Min Act: -0.1700

Data Index: 1492343 (Python Code)

Max Activating Token Index: 277

Text #4

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.1640. Min Act: -0.1700

Data Index: 1542178 (Python Code)

Max Activating Token Index: 911

Text #5

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.1405. Min Act: -0.1700

Data Index: 1518593 (Python Code)

Max Activating Token Index: 158

Text #6

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.1378. Min Act: -0.1700

Data Index: 1444272 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.1215. Min Act: -0.1700

Data Index: 1484676 (Python Code)

Max Activating Token Index: 750

Text #8

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.1417. Min Act: -0.1700

Data Index: 626256 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.1240. Min Act: -0.1700

Data Index: 1397781 (Python Code)

Max Activating Token Index: 144

Text #10

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.1074. Min Act: -0.1700

Data Index: 1419860 (Python Code)

Max Activating Token Index: 135

Text #11

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.1152. Min Act: -0.1700

Data Index: 918607 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.0856. Min Act: -0.1700

Data Index: 702894 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.1048. Min Act: -0.1700

Data Index: 1483915 (Python Code)

Max Activating Token Index: 918

Text #14

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.0999. Min Act: -0.1700

Data Index: 1614992 (Python Code)

Max Activating Token Index: 399

Text #15

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.1089. Min Act: -0.1700

Data Index: 1368096 (Python Code)

Max Activating Token Index: 989

Text #16

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.0836. Min Act: -0.1700

Data Index: 1256336 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.1100. Min Act: -0.1700

Data Index: 1104549 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.0888. Min Act: -0.1700

Data Index: 1172689 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 3.2332. Min Range: -3.2332

Max Act: 3.0721. Min Act: -0.1700

Data Index: 1234808 (C4 (Web Text))

Max Activating Token Index: 232