Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 528 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.2652. Min Act: -0.1700

Data Index: 3459 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.2023. Min Act: -0.1700

Data Index: 860289 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1866. Min Act: -0.1700

Data Index: 493863 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1393. Min Act: -0.1700

Data Index: 640566 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1078. Min Act: -0.1700

Data Index: 840771 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0921. Min Act: -0.1700

Data Index: 547352 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0763. Min Act: -0.1700

Data Index: 312350 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0921. Min Act: -0.1700

Data Index: 968707 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0763. Min Act: -0.1700

Data Index: 640781 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0447. Min Act: -0.1700

Data Index: 235566 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0605. Min Act: -0.1700

Data Index: 852782 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0447. Min Act: -0.1700

Data Index: 1021210 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0131. Min Act: -0.1700

Data Index: 420589 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0447. Min Act: -0.1700

Data Index: 191450 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0447. Min Act: -0.1700

Data Index: 509637 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0289. Min Act: -0.1700

Data Index: 1061327 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0131. Min Act: -0.1700

Data Index: 1318627 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0447. Min Act: -0.1700

Data Index: 584478 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 3.2652. Min Range: -3.2652

Max Act: 2.9973. Min Act: -0.1700

Data Index: 628853 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.0289. Min Act: -0.1700

Data Index: 885983 (C4 (Web Text))

Max Activating Token Index: 993