Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1975 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.4090. Min Act: -0.1700

Data Index: 693468 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.2683. Min Act: -0.1700

Data Index: 825601 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.2527. Min Act: -0.1700

Data Index: 771574 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.2371. Min Act: -0.1700

Data Index: 1114969 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.2371. Min Act: -0.1700

Data Index: 388569 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.1902. Min Act: -0.1700

Data Index: 1286076 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.2058. Min Act: -0.1700

Data Index: 99359 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.1589. Min Act: -0.1700

Data Index: 1021580 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.1589. Min Act: -0.1700

Data Index: 943664 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.1589. Min Act: -0.1700

Data Index: 342107 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.1277. Min Act: -0.1700

Data Index: 841080 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.1433. Min Act: -0.1700

Data Index: 664220 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.0964. Min Act: -0.1700

Data Index: 302864 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.0964. Min Act: -0.1700

Data Index: 150718 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.1121. Min Act: -0.1700

Data Index: 1336822 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.0652. Min Act: -0.1700

Data Index: 362693 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.0652. Min Act: -0.1700

Data Index: 406523 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.0964. Min Act: -0.1700

Data Index: 270564 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.0495. Min Act: -0.1700

Data Index: 1356372 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 4.4090. Min Range: -4.4090

Max Act: 4.0026. Min Act: -0.1700

Data Index: 427814 (C4 (Web Text))

Max Activating Token Index: 947