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

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

Neuron 1549 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: 4.7788. Min Range: -4.7788

Max Act: 4.7788. Min Act: -0.1700

Data Index: 452806 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.7309. Min Act: -0.1700

Data Index: 372451 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.6625. Min Act: -0.1700

Data Index: 312544 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.6734. Min Act: -0.1700

Data Index: 595086 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.6218. Min Act: -0.1700

Data Index: 1029276 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.4937. Min Act: -0.1700

Data Index: 891496 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.4412. Min Act: -0.1700

Data Index: 1036807 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.4391. Min Act: -0.1700

Data Index: 250857 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.4633. Min Act: -0.1700

Data Index: 463557 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.4047. Min Act: -0.1700

Data Index: 822060 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.3888. Min Act: -0.1700

Data Index: 590237 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.3730. Min Act: -0.1700

Data Index: 612505 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.3731. Min Act: -0.1700

Data Index: 254486 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.3812. Min Act: -0.1700

Data Index: 594383 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.3566. Min Act: -0.1700

Data Index: 515005 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.3590. Min Act: -0.1700

Data Index: 704104 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.3614. Min Act: -0.1700

Data Index: 197177 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.3664. Min Act: -0.1700

Data Index: 706606 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.3261. Min Act: -0.1699

Data Index: 380871 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 4.7788. Min Range: -4.7788

Max Act: 4.2884. Min Act: -0.1699

Data Index: 764021 (C4 (Web Text))

Max Activating Token Index: 674