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

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

Neuron 1927 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: 3.8438. Min Range: -3.8438

Max Act: 3.8438. Min Act: -0.1700

Data Index: 250258 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.7500. Min Act: -0.1700

Data Index: 52302 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.6092. Min Act: -0.1700

Data Index: 82547 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.6092. Min Act: -0.1700

Data Index: 800063 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.5778. Min Act: -0.1700

Data Index: 1117702 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.5622. Min Act: -0.1700

Data Index: 321663 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.5465. Min Act: -0.1700

Data Index: 716752 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4838. Min Act: -0.1700

Data Index: 694900 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.5152. Min Act: -0.1700

Data Index: 996254 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.5308. Min Act: -0.1700

Data Index: 497899 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4995. Min Act: -0.1700

Data Index: 1265915 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4055. Min Act: -0.1700

Data Index: 1349366 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4682. Min Act: -0.1700

Data Index: 1233724 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4995. Min Act: -0.1700

Data Index: 760745 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4211. Min Act: -0.1700

Data Index: 850557 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4838. Min Act: -0.1700

Data Index: 319765 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4995. Min Act: -0.1700

Data Index: 410845 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4525. Min Act: -0.1699

Data Index: 976125 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4055. Min Act: -0.1700

Data Index: 1959 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 3.8438. Min Range: -3.8438

Max Act: 3.4368. Min Act: -0.1700

Data Index: 691321 (C4 (Web Text))

Max Activating Token Index: 965