Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1878 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.6570. Min Act: -0.1700

Data Index: 522175 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.4848. Min Act: -0.1700

Data Index: 520792 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.4534. Min Act: -0.1700

Data Index: 889491 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.4691. Min Act: -0.1700

Data Index: 937734 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.4221. Min Act: -0.1700

Data Index: 137896 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.3907. Min Act: -0.1700

Data Index: 195264 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.3907. Min Act: -0.1700

Data Index: 1111116 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.3907. Min Act: -0.1700

Data Index: 1207600 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.4221. Min Act: -0.1700

Data Index: 963837 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.3907. Min Act: -0.1700

Data Index: 1350745 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.3593. Min Act: -0.1700

Data Index: 408210 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.3593. Min Act: -0.1700

Data Index: 15182 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.3750. Min Act: -0.1700

Data Index: 22007 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.3593. Min Act: -0.1700

Data Index: 1089782 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.3593. Min Act: -0.1700

Data Index: 722985 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.3436. Min Act: -0.1700

Data Index: 331859 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.3122. Min Act: -0.1700

Data Index: 355431 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.3279. Min Act: -0.1700

Data Index: 850845 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.2808. Min Act: -0.1700

Data Index: 1060589 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.3122. Min Act: -0.1700

Data Index: 365682 (C4 (Web Text))

Max Activating Token Index: 846