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

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

Neuron 178 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0754. Min Range: -5.0754

Max Act: 5.0754. Min Act: -0.1700

Data Index: 592411 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 5.0754. Min Range: -5.0754

Max Act: 5.0129. Min Act: -0.1700

Data Index: 1214680 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.8879. Min Act: -0.1700

Data Index: 1048997 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.8566. Min Act: -0.1700

Data Index: 808138 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.8254. Min Act: -0.1700

Data Index: 555400 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.8566. Min Act: -0.1700

Data Index: 464582 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.8879. Min Act: -0.1700

Data Index: 138153 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.7941. Min Act: -0.1700

Data Index: 923912 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.7629. Min Act: -0.1700

Data Index: 166403 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.7941. Min Act: -0.1700

Data Index: 135305 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.7629. Min Act: -0.1700

Data Index: 181519 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.7941. Min Act: -0.1700

Data Index: 1112307 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.7941. Min Act: -0.1700

Data Index: 661445 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.8566. Min Act: -0.1700

Data Index: 456833 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.7629. Min Act: -0.1700

Data Index: 804503 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.7629. Min Act: -0.1700

Data Index: 806047 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.7004. Min Act: -0.1700

Data Index: 854901 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.7941. Min Act: -0.1700

Data Index: 915756 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.8254. Min Act: -0.1700

Data Index: 1244137 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 5.0754. Min Range: -5.0754

Max Act: 4.7629. Min Act: -0.1700

Data Index: 53025 (C4 (Web Text))

Max Activating Token Index: 321