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

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

Neuron 176 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: 3.0693. Min Range: -3.0693

Max Act: 3.0693. Min Act: -0.1700

Data Index: 1598000 (Python Code)

Max Activating Token Index: 168

Text #1

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.9280. Min Act: -0.1700

Data Index: 1580993 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.8987. Min Act: -0.1700

Data Index: 1427834 (Python Code)

Max Activating Token Index: 629

Text #3

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.8606. Min Act: -0.1700

Data Index: 1639813 (Python Code)

Max Activating Token Index: 831

Text #4

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.8502. Min Act: -0.1700

Data Index: 1434144 (Python Code)

Max Activating Token Index: 138

Text #5

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.8284. Min Act: -0.1630

Data Index: 215222 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.8276. Min Act: -0.1696

Data Index: 1538139 (Python Code)

Max Activating Token Index: 676

Text #7

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.8255. Min Act: -0.1699

Data Index: 1524019 (Python Code)

Max Activating Token Index: 800

Text #8

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.7834. Min Act: -0.1700

Data Index: 1582047 (Python Code)

Max Activating Token Index: 88

Text #9

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.7849. Min Act: -0.1178

Data Index: 1296005 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.7651. Min Act: -0.1699

Data Index: 1451318 (Python Code)

Max Activating Token Index: 947

Text #11

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.7570. Min Act: -0.1700

Data Index: 1560331 (Python Code)

Max Activating Token Index: 282

Text #12

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.7624. Min Act: -0.1697

Data Index: 1539606 (Python Code)

Max Activating Token Index: 408

Text #13

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.7511. Min Act: -0.1661

Data Index: 1654013 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.7378. Min Act: -0.1700

Data Index: 1364700 (Python Code)

Max Activating Token Index: 75

Text #15

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.7284. Min Act: -0.1669

Data Index: 1362457 (Python Code)

Max Activating Token Index: 783

Text #16

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.7344. Min Act: -0.1698

Data Index: 1491796 (Python Code)

Max Activating Token Index: 595

Text #17

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.7287. Min Act: -0.1698

Data Index: 1533266 (Python Code)

Max Activating Token Index: 73

Text #18

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.7327. Min Act: -0.1700

Data Index: 1391763 (Python Code)

Max Activating Token Index: 689

Text #19

Max Range: 3.0693. Min Range: -3.0693

Max Act: 2.7158. Min Act: -0.1592

Data Index: 1613115 (Python Code)

Max Activating Token Index: 730