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

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

Neuron 93 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: 5.1276. Min Range: -5.1276

Max Act: 5.1276. Min Act: -0.1700

Data Index: 1539466 (Python Code)

Max Activating Token Index: 463

Text #1

Max Range: 5.1276. Min Range: -5.1276

Max Act: 5.0665. Min Act: -0.1700

Data Index: 1536821 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.9786. Min Act: -0.1700

Data Index: 1512505 (Python Code)

Max Activating Token Index: 927

Text #3

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.9303. Min Act: -0.1697

Data Index: 1495371 (Python Code)

Max Activating Token Index: 580

Text #4

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.9210. Min Act: -0.1700

Data Index: 1492960 (Python Code)

Max Activating Token Index: 122

Text #5

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.9207. Min Act: -0.1700

Data Index: 1517182 (Python Code)

Max Activating Token Index: 542

Text #6

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.9083. Min Act: -0.1700

Data Index: 1429558 (Python Code)

Max Activating Token Index: 248

Text #7

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.8953. Min Act: -0.1700

Data Index: 1522503 (Python Code)

Max Activating Token Index: 721

Text #8

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.8906. Min Act: -0.1695

Data Index: 1393665 (Python Code)

Max Activating Token Index: 385

Text #9

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.8611. Min Act: -0.1699

Data Index: 1530862 (Python Code)

Max Activating Token Index: 76

Text #10

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.8393. Min Act: -0.1700

Data Index: 1448334 (Python Code)

Max Activating Token Index: 332

Text #11

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.8325. Min Act: -0.1700

Data Index: 1375493 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.7826. Min Act: -0.1700

Data Index: 1398510 (Python Code)

Max Activating Token Index: 324

Text #13

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.8130. Min Act: -0.1700

Data Index: 1610235 (Python Code)

Max Activating Token Index: 397

Text #14

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.8046. Min Act: -0.1521

Data Index: 1455755 (Python Code)

Max Activating Token Index: 56

Text #15

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.7967. Min Act: -0.1685

Data Index: 1562779 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.8065. Min Act: -0.1697

Data Index: 1640651 (Python Code)

Max Activating Token Index: 378

Text #17

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.8110. Min Act: -0.1700

Data Index: 1395473 (Python Code)

Max Activating Token Index: 570

Text #18

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.7470. Min Act: -0.1700

Data Index: 1574577 (Python Code)

Max Activating Token Index: 156

Text #19

Max Range: 5.1276. Min Range: -5.1276

Max Act: 4.7798. Min Act: -0.1699

Data Index: 1600516 (Python Code)

Max Activating Token Index: 316