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

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

Neuron 39 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: 3.7979. Min Range: -3.7979

Max Act: 3.7979. Min Act: -0.1700

Data Index: 1100259 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.7666. Min Act: -0.1700

Data Index: 282833 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.7979. Min Act: -0.1700

Data Index: 1137360 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.7041. Min Act: -0.1700

Data Index: 841732 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.7666. Min Act: -0.1700

Data Index: 1094661 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.7041. Min Act: -0.1700

Data Index: 563100 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.7041. Min Act: -0.1700

Data Index: 66109 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.7041. Min Act: -0.1700

Data Index: 158575 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.7354. Min Act: -0.1700

Data Index: 1160746 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.6728. Min Act: -0.1700

Data Index: 769623 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.7354. Min Act: -0.1700

Data Index: 734234 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.6728. Min Act: -0.1700

Data Index: 994063 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.7354. Min Act: -0.1700

Data Index: 240485 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.6102. Min Act: -0.1700

Data Index: 613180 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.6728. Min Act: -0.1700

Data Index: 1203718 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.6728. Min Act: -0.1700

Data Index: 1326003 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.6102. Min Act: -0.1700

Data Index: 476656 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.6728. Min Act: -0.1700

Data Index: 134 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.6415. Min Act: -0.1700

Data Index: 785274 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 3.7979. Min Range: -3.7979

Max Act: 3.6102. Min Act: -0.1700

Data Index: 1229998 (C4 (Web Text))

Max Activating Token Index: 975