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

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

Neuron 1808 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: 6.3059. Min Range: -6.3059

Max Act: 6.3059. Min Act: -0.1700

Data Index: 1470438 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 6.3059. Min Range: -6.3059

Max Act: 6.2493. Min Act: -0.1700

Data Index: 1434166 (Python Code)

Max Activating Token Index: 912

Text #2

Max Range: 6.3059. Min Range: -6.3059

Max Act: 6.2366. Min Act: -0.1700

Data Index: 1632443 (Python Code)

Max Activating Token Index: 848

Text #3

Max Range: 6.3059. Min Range: -6.3059

Max Act: 6.1329. Min Act: -0.1700

Data Index: 1585949 (Python Code)

Max Activating Token Index: 387

Text #4

Max Range: 6.3059. Min Range: -6.3059

Max Act: 6.0527. Min Act: -0.1700

Data Index: 1379211 (Python Code)

Max Activating Token Index: 583

Text #5

Max Range: 6.3059. Min Range: -6.3059

Max Act: 6.0691. Min Act: -0.1700

Data Index: 1601263 (Python Code)

Max Activating Token Index: 34

Text #6

Max Range: 6.3059. Min Range: -6.3059

Max Act: 6.0423. Min Act: -0.1700

Data Index: 1534620 (Python Code)

Max Activating Token Index: 113

Text #7

Max Range: 6.3059. Min Range: -6.3059

Max Act: 5.9917. Min Act: -0.1700

Data Index: 1564326 (Python Code)

Max Activating Token Index: 672

Text #8

Max Range: 6.3059. Min Range: -6.3059

Max Act: 6.0142. Min Act: -0.1700

Data Index: 1562956 (Python Code)

Max Activating Token Index: 690

Text #9

Max Range: 6.3059. Min Range: -6.3059

Max Act: 5.9919. Min Act: -0.1700

Data Index: 1562696 (Python Code)

Max Activating Token Index: 769

Text #10

Max Range: 6.3059. Min Range: -6.3059

Max Act: 5.9807. Min Act: -0.1700

Data Index: 1379401 (Python Code)

Max Activating Token Index: 553

Text #11

Max Range: 6.3059. Min Range: -6.3059

Max Act: 5.9865. Min Act: -0.1700

Data Index: 1446447 (Python Code)

Max Activating Token Index: 685

Text #12

Max Range: 6.3059. Min Range: -6.3059

Max Act: 5.9581. Min Act: -0.1700

Data Index: 1643779 (Python Code)

Max Activating Token Index: 644

Text #13

Max Range: 6.3059. Min Range: -6.3059

Max Act: 5.9601. Min Act: -0.1700

Data Index: 1636545 (Python Code)

Max Activating Token Index: 604

Text #14

Max Range: 6.3059. Min Range: -6.3059

Max Act: 5.9280. Min Act: -0.1700

Data Index: 1472491 (Python Code)

Max Activating Token Index: 220

Text #15

Max Range: 6.3059. Min Range: -6.3059

Max Act: 5.9390. Min Act: -0.1700

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 6.3059. Min Range: -6.3059

Max Act: 5.8738. Min Act: -0.1700

Data Index: 1520875 (Python Code)

Max Activating Token Index: 677

Text #17

Max Range: 6.3059. Min Range: -6.3059

Max Act: 5.8463. Min Act: -0.1700

Data Index: 1536171 (Python Code)

Max Activating Token Index: 495

Text #18

Max Range: 6.3059. Min Range: -6.3059

Max Act: 5.8472. Min Act: -0.1700

Data Index: 1632237 (Python Code)

Max Activating Token Index: 124

Text #19

Max Range: 6.3059. Min Range: -6.3059

Max Act: 5.8364. Min Act: -0.1700

Data Index: 1439303 (Python Code)

Max Activating Token Index: 202