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

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

Neuron 1698 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: 3.6801. Min Range: -3.6801

Max Act: 3.6488. Min Act: -0.1700

Data Index: 542276 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.6488. Min Act: -0.1700

Data Index: 774817 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.6801. Min Act: -0.1700

Data Index: 1293633 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.6645. Min Act: -0.1700

Data Index: 830242 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.6019. Min Act: -0.1700

Data Index: 682818 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.6488. Min Act: -0.1700

Data Index: 747641 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.6645. Min Act: -0.1700

Data Index: 323485 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.6019. Min Act: -0.1700

Data Index: 1001335 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.5862. Min Act: -0.1700

Data Index: 406808 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.5549. Min Act: -0.1700

Data Index: 895181 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.4452. Min Act: -0.1700

Data Index: 932947 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.5235. Min Act: -0.1700

Data Index: 407794 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.6019. Min Act: -0.1700

Data Index: 388679 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.4609. Min Act: -0.1700

Data Index: 653322 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.5392. Min Act: -0.1700

Data Index: 531880 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.5235. Min Act: -0.1700

Data Index: 1004622 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.4765. Min Act: -0.1700

Data Index: 1177018 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.4922. Min Act: -0.1700

Data Index: 330578 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.4922. Min Act: -0.1700

Data Index: 213561 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 3.6801. Min Range: -3.6801

Max Act: 3.4922. Min Act: -0.1700

Data Index: 571481 (C4 (Web Text))

Max Activating Token Index: 610