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

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

Neuron 441 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: 3.3374. Min Range: -3.3374

Max Act: 3.3374. Min Act: -0.1700

Data Index: 92040 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.2563. Min Act: -0.1700

Data Index: 401493 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.2351. Min Act: -0.1700

Data Index: 667669 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.2257. Min Act: -0.1700

Data Index: 1207233 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.1795. Min Act: -0.1700

Data Index: 358421 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.1474. Min Act: -0.1700

Data Index: 293919 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.1483. Min Act: -0.1700

Data Index: 590508 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.1268. Min Act: -0.1700

Data Index: 462504 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.1283. Min Act: -0.1700

Data Index: 1176493 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.1053. Min Act: -0.1700

Data Index: 1436593 (Python Code)

Max Activating Token Index: 874

Text #10

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.1090. Min Act: -0.1699

Data Index: 282604 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.0885. Min Act: -0.1700

Data Index: 967125 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.0841. Min Act: -0.1700

Data Index: 233778 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.0887. Min Act: -0.1700

Data Index: 410452 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.0875. Min Act: -0.1700

Data Index: 1453110 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.0906. Min Act: -0.1700

Data Index: 840542 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.0680. Min Act: -0.1700

Data Index: 940865 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.0684. Min Act: -0.1700

Data Index: 97764 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.0685. Min Act: -0.1700

Data Index: 129061 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 3.3374. Min Range: -3.3374

Max Act: 3.0654. Min Act: -0.1700

Data Index: 752394 (C4 (Web Text))

Max Activating Token Index: 466