Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1872 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.5517. Min Act: -0.0970

Data Index: 737703 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.4283. Min Act: -0.1700

Data Index: 1143311 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.4418. Min Act: -0.1700

Data Index: 871641 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.3942. Min Act: -0.1700

Data Index: 400647 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.3524. Min Act: -0.0970

Data Index: 953287 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.3518. Min Act: -0.1117

Data Index: 1173771 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.3351. Min Act: -0.1698

Data Index: 799938 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.3347. Min Act: -0.0970

Data Index: 714849 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.3211. Min Act: -0.1700

Data Index: 814641 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.3376. Min Act: -0.0970

Data Index: 461513 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.3323. Min Act: -0.1700

Data Index: 765331 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.3402. Min Act: -0.1700

Data Index: 958913 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.2902. Min Act: -0.1694

Data Index: 404908 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.2911. Min Act: -0.1700

Data Index: 1207408 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.2842. Min Act: -0.1700

Data Index: 547359 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.3025. Min Act: -0.1700

Data Index: 665815 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.2819. Min Act: -0.1700

Data Index: 1074936 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.2557. Min Act: -0.1700

Data Index: 1072742 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.2648. Min Act: -0.1477

Data Index: 106824 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 3.5517. Min Range: -3.5517

Max Act: 3.2699. Min Act: -0.1700

Data Index: 127580 (C4 (Web Text))

Max Activating Token Index: 53