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

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

Neuron 1558 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.1940. Min Act: -0.1700

Data Index: 262623 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.1784. Min Act: -0.1700

Data Index: 653685 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.1315. Min Act: -0.1700

Data Index: 329974 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.1628. Min Act: -0.1700

Data Index: 782483 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0847. Min Act: -0.1700

Data Index: 1019302 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.1003. Min Act: -0.1700

Data Index: 531236 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.1003. Min Act: -0.1700

Data Index: 116193 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0378. Min Act: -0.1700

Data Index: 495582 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0847. Min Act: -0.1700

Data Index: 1114454 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0534. Min Act: -0.1700

Data Index: 284897 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0690. Min Act: -0.1700

Data Index: 680105 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0378. Min Act: -0.1700

Data Index: 976997 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0222. Min Act: -0.1700

Data Index: 773643 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0534. Min Act: -0.1700

Data Index: 3323 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9597. Min Act: -0.1700

Data Index: 936992 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0222. Min Act: -0.1700

Data Index: 761676 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0378. Min Act: -0.1700

Data Index: 830713 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9909. Min Act: -0.1700

Data Index: 1329320 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0534. Min Act: -0.1700

Data Index: 330859 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0378. Min Act: -0.1700

Data Index: 1073729 (C4 (Web Text))

Max Activating Token Index: 876