Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1916 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0766. Min Range: -5.0766

Max Act: 5.0766. Min Act: -0.1700

Data Index: 866945 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 5.0766. Min Range: -5.0766

Max Act: 5.0454. Min Act: -0.1700

Data Index: 836328 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 5.0766. Min Range: -5.0766

Max Act: 5.0454. Min Act: -0.1700

Data Index: 775976 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.9829. Min Act: -0.1700

Data Index: 782674 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.9829. Min Act: -0.1700

Data Index: 243558 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.9516. Min Act: -0.1700

Data Index: 269120 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.9204. Min Act: -0.1700

Data Index: 73475 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.8891. Min Act: -0.1700

Data Index: 352304 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.8891. Min Act: -0.1700

Data Index: 520265 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.8266. Min Act: -0.1700

Data Index: 501866 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.8579. Min Act: -0.1700

Data Index: 347354 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.9204. Min Act: -0.1700

Data Index: 64176 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.9204. Min Act: -0.1700

Data Index: 155349 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.8579. Min Act: -0.1700

Data Index: 826264 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.7954. Min Act: -0.1700

Data Index: 160156 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.8266. Min Act: -0.1700

Data Index: 751798 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.7329. Min Act: -0.1700

Data Index: 565337 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.7954. Min Act: -0.1700

Data Index: 406270 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.7954. Min Act: -0.1700

Data Index: 485654 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 5.0766. Min Range: -5.0766

Max Act: 4.7329. Min Act: -0.1700

Data Index: 774921 (C4 (Web Text))

Max Activating Token Index: 15