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

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

Neuron 1973 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: 5.7432. Min Range: -5.7432

Max Act: 5.7432. Min Act: -0.1700

Data Index: 363797 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.6807. Min Act: -0.1700

Data Index: 724981 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.6495. Min Act: -0.1700

Data Index: 231420 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.6495. Min Act: -0.1691

Data Index: 83991 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.6495. Min Act: -0.1700

Data Index: 943994 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.5557. Min Act: -0.1700

Data Index: 1190142 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.5245. Min Act: -0.1700

Data Index: 1100289 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.5557. Min Act: -0.1700

Data Index: 1039559 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.5245. Min Act: -0.1700

Data Index: 160860 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.5245. Min Act: -0.1700

Data Index: 1132626 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.5557. Min Act: -0.1687

Data Index: 483353 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.5245. Min Act: -0.1699

Data Index: 659797 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.4620. Min Act: -0.1700

Data Index: 515003 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.4307. Min Act: -0.1696

Data Index: 1270380 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.4307. Min Act: -0.1700

Data Index: 558302 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.4307. Min Act: -0.1695

Data Index: 403144 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.4307. Min Act: -0.1699

Data Index: 275122 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.4620. Min Act: -0.1700

Data Index: 1024385 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.3995. Min Act: -0.1700

Data Index: 820319 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 5.7432. Min Range: -5.7432

Max Act: 5.4620. Min Act: -0.1700

Data Index: 589835 (C4 (Web Text))

Max Activating Token Index: 708