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

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

Neuron 1709 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: 5.7068. Min Range: -5.7068

Max Act: 5.7068. Min Act: -0.1700

Data Index: 115544 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 5.7068. Min Range: -5.7068

Max Act: 5.3318. Min Act: -0.1700

Data Index: 274863 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 5.7068. Min Range: -5.7068

Max Act: 5.1755. Min Act: -0.1700

Data Index: 1137008 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 5.7068. Min Range: -5.7068

Max Act: 5.1755. Min Act: -0.1700

Data Index: 462855 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 5.7068. Min Range: -5.7068

Max Act: 5.1130. Min Act: -0.1700

Data Index: 609924 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 5.7068. Min Range: -5.7068

Max Act: 5.0818. Min Act: -0.1699

Data Index: 1004558 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 5.7068. Min Range: -5.7068

Max Act: 5.0818. Min Act: -0.1700

Data Index: 1140039 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 5.7068. Min Range: -5.7068

Max Act: 5.0818. Min Act: -0.1700

Data Index: 951783 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 5.7068. Min Range: -5.7068

Max Act: 5.0818. Min Act: -0.1700

Data Index: 1248600 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 5.7068. Min Range: -5.7068

Max Act: 5.0193. Min Act: -0.1699

Data Index: 188631 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 5.7068. Min Range: -5.7068

Max Act: 5.0193. Min Act: -0.1700

Data Index: 75078 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 5.7068. Min Range: -5.7068

Max Act: 4.9411. Min Act: -0.1700

Data Index: 634008 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 5.7068. Min Range: -5.7068

Max Act: 4.9099. Min Act: -0.1700

Data Index: 522415 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 5.7068. Min Range: -5.7068

Max Act: 4.8943. Min Act: -0.1700

Data Index: 844242 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 5.7068. Min Range: -5.7068

Max Act: 4.8630. Min Act: -0.1700

Data Index: 214070 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 5.7068. Min Range: -5.7068

Max Act: 4.8786. Min Act: -0.1700

Data Index: 1356985 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 5.7068. Min Range: -5.7068

Max Act: 4.8630. Min Act: -0.1700

Data Index: 269860 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 5.7068. Min Range: -5.7068

Max Act: 4.8474. Min Act: -0.1700

Data Index: 1233114 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 5.7068. Min Range: -5.7068

Max Act: 4.8318. Min Act: -0.1700

Data Index: 179825 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 5.7068. Min Range: -5.7068

Max Act: 4.8318. Min Act: -0.1700

Data Index: 1064058 (C4 (Web Text))

Max Activating Token Index: 214