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

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

Neuron 769 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: 3.7881. Min Range: -3.7881

Max Act: 3.7881. Min Act: -0.1700

Data Index: 1204497 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.7724. Min Act: -0.1700

Data Index: 595863 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.7411. Min Act: -0.1700

Data Index: 674068 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.7255. Min Act: -0.1700

Data Index: 1069399 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6942. Min Act: -0.1700

Data Index: 755565 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6785. Min Act: -0.1700

Data Index: 1201986 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6472. Min Act: -0.1700

Data Index: 1268004 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6159. Min Act: -0.1700

Data Index: 224949 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6316. Min Act: -0.1700

Data Index: 116851 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6159. Min Act: -0.1700

Data Index: 453992 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6629. Min Act: -0.1700

Data Index: 721199 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.5846. Min Act: -0.1700

Data Index: 709468 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6472. Min Act: -0.1700

Data Index: 524247 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6316. Min Act: -0.1700

Data Index: 1069938 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6003. Min Act: -0.1700

Data Index: 35059 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6316. Min Act: -0.1700

Data Index: 1118852 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6003. Min Act: -0.1700

Data Index: 779672 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6472. Min Act: -0.1700

Data Index: 879868 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.5690. Min Act: -0.1700

Data Index: 241839 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 3.7881. Min Range: -3.7881

Max Act: 3.6003. Min Act: -0.1700

Data Index: 174729 (C4 (Web Text))

Max Activating Token Index: 399