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

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

Neuron 1530 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: 3.9593. Min Range: -3.9593

Max Act: 3.9281. Min Act: -0.1700

Data Index: 786864 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.9593. Min Act: -0.1700

Data Index: 465354 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.9281. Min Act: -0.1700

Data Index: 407860 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8655. Min Act: -0.1700

Data Index: 128196 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8968. Min Act: -0.1700

Data Index: 602360 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8655. Min Act: -0.1700

Data Index: 1184325 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8968. Min Act: -0.1700

Data Index: 807666 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8342. Min Act: -0.1700

Data Index: 994275 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8655. Min Act: -0.1700

Data Index: 516780 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8968. Min Act: -0.1700

Data Index: 174374 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8030. Min Act: -0.1700

Data Index: 909783 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8655. Min Act: -0.1700

Data Index: 868537 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8342. Min Act: -0.1700

Data Index: 556408 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8342. Min Act: -0.1700

Data Index: 817955 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8342. Min Act: -0.1700

Data Index: 178391 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8030. Min Act: -0.1700

Data Index: 661218 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.7717. Min Act: -0.1700

Data Index: 459026 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.8030. Min Act: -0.1700

Data Index: 226674 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.7717. Min Act: -0.1700

Data Index: 23339 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 3.9593. Min Range: -3.9593

Max Act: 3.7404. Min Act: -0.1700

Data Index: 935013 (C4 (Web Text))

Max Activating Token Index: 407