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

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

Neuron 1638 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: 4.1921. Min Range: -4.1921

Max Act: 4.1921. Min Act: -0.1700

Data Index: 620593 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 4.1921. Min Range: -4.1921

Max Act: 4.1765. Min Act: -0.1700

Data Index: 697478 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 4.1921. Min Range: -4.1921

Max Act: 4.0983. Min Act: -0.1700

Data Index: 1062107 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 4.1921. Min Range: -4.1921

Max Act: 4.1296. Min Act: -0.1700

Data Index: 958464 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 4.1921. Min Range: -4.1921

Max Act: 4.0827. Min Act: -0.1700

Data Index: 223723 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 4.1921. Min Range: -4.1921

Max Act: 4.0514. Min Act: -0.1700

Data Index: 736268 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 4.1921. Min Range: -4.1921

Max Act: 4.1140. Min Act: -0.1700

Data Index: 48748 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 4.1921. Min Range: -4.1921

Max Act: 3.9889. Min Act: -0.1700

Data Index: 196073 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 4.1921. Min Range: -4.1921

Max Act: 4.0671. Min Act: -0.1700

Data Index: 645631 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 4.1921. Min Range: -4.1921

Max Act: 4.0514. Min Act: -0.1700

Data Index: 401001 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 4.1921. Min Range: -4.1921

Max Act: 4.0358. Min Act: -0.1700

Data Index: 1219384 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 4.1921. Min Range: -4.1921

Max Act: 4.0202. Min Act: -0.1700

Data Index: 15543 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 4.1921. Min Range: -4.1921

Max Act: 4.0514. Min Act: -0.1700

Data Index: 626371 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 4.1921. Min Range: -4.1921

Max Act: 3.9889. Min Act: -0.1700

Data Index: 14149 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 4.1921. Min Range: -4.1921

Max Act: 3.9889. Min Act: -0.1700

Data Index: 823002 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 4.1921. Min Range: -4.1921

Max Act: 4.0045. Min Act: -0.1700

Data Index: 910137 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 4.1921. Min Range: -4.1921

Max Act: 3.9733. Min Act: -0.1700

Data Index: 1037949 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 4.1921. Min Range: -4.1921

Max Act: 3.9576. Min Act: -0.1700

Data Index: 1046941 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 4.1921. Min Range: -4.1921

Max Act: 3.9420. Min Act: -0.1700

Data Index: 584642 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 4.1921. Min Range: -4.1921

Max Act: 3.9420. Min Act: -0.1700

Data Index: 161109 (C4 (Web Text))

Max Activating Token Index: 97