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

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

Neuron 798 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: 5.4111. Min Range: -5.4111

Max Act: 5.4111. Min Act: -0.1700

Data Index: 275035 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.3174. Min Act: -0.1700

Data Index: 509200 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.2236. Min Act: -0.1700

Data Index: 1166144 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.1924. Min Act: -0.1700

Data Index: 167776 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.1611. Min Act: -0.1700

Data Index: 799657 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.1611. Min Act: -0.1700

Data Index: 836100 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.1299. Min Act: -0.1700

Data Index: 1297062 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.1611. Min Act: -0.1700

Data Index: 543514 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.1924. Min Act: -0.1700

Data Index: 1215011 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.0986. Min Act: -0.1700

Data Index: 1093737 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.0674. Min Act: -0.1700

Data Index: 1044299 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.0674. Min Act: -0.1700

Data Index: 39895 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.0361. Min Act: -0.1700

Data Index: 601363 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.0674. Min Act: -0.1700

Data Index: 1343693 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.0361. Min Act: -0.1700

Data Index: 21010 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.0361. Min Act: -0.1699

Data Index: 1286735 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.0361. Min Act: -0.1700

Data Index: 1278177 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.0361. Min Act: -0.1700

Data Index: 452165 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.0361. Min Act: -0.1700

Data Index: 511535 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 5.4111. Min Range: -5.4111

Max Act: 5.0674. Min Act: -0.1700

Data Index: 738684 (C4 (Web Text))

Max Activating Token Index: 550