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

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

Neuron 224 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: 4.5471. Min Range: -4.5471

Max Act: 4.5471. Min Act: -0.1700

Data Index: 53115 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.4812. Min Act: -0.1700

Data Index: 1644685 (Python Code)

Max Activating Token Index: 618

Text #2

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.4547. Min Act: -0.1700

Data Index: 916872 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.3958. Min Act: -0.1700

Data Index: 1148368 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.3282. Min Act: -0.1700

Data Index: 170356 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.2942. Min Act: -0.1700

Data Index: 1113703 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.2889. Min Act: -0.1699

Data Index: 1625753 (Python Code)

Max Activating Token Index: 1022

Text #7

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.2813. Min Act: -0.1700

Data Index: 562494 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.2776. Min Act: -0.1700

Data Index: 187703 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.2251. Min Act: -0.1699

Data Index: 766100 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.2473. Min Act: -0.1700

Data Index: 1181128 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.2043. Min Act: -0.1700

Data Index: 715341 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1932. Min Act: -0.1700

Data Index: 633109 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1904. Min Act: -0.1700

Data Index: 1238973 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.2109. Min Act: -0.1699

Data Index: 47797 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1565. Min Act: -0.1699

Data Index: 1087182 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1732. Min Act: -0.1700

Data Index: 1167738 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1635. Min Act: -0.1700

Data Index: 452865 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1877. Min Act: -0.1700

Data Index: 435387 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 4.5471. Min Range: -4.5471

Max Act: 4.1832. Min Act: -0.1700

Data Index: 1599637 (Python Code)

Max Activating Token Index: 117