Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2180 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.0668. Min Range: -4.0668

Max Act: 4.0668. Min Act: -0.1700

Data Index: 4986929 (Open Web Text)

Max Activating Token Index: 712

Text #1

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9875. Min Act: -0.1700

Data Index: 3980706 (Open Web Text)

Max Activating Token Index: 565

Text #2

Max Range: 4.0668. Min Range: -4.0668

Max Act: 4.0007. Min Act: -0.1700

Data Index: 2595663 (Open Web Text)

Max Activating Token Index: 818

Text #3

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9695. Min Act: -0.1700

Data Index: 5943873 (Open Web Text)

Max Activating Token Index: 754

Text #4

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9734. Min Act: -0.1700

Data Index: 3691309 (Open Web Text)

Max Activating Token Index: 397

Text #5

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9854. Min Act: -0.1700

Data Index: 3181050 (Open Web Text)

Max Activating Token Index: 588

Text #6

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9826. Min Act: -0.1700

Data Index: 7120840 (Open Web Text)

Max Activating Token Index: 522

Text #7

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9722. Min Act: -0.1700

Data Index: 7020873 (Open Web Text)

Max Activating Token Index: 658

Text #8

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9573. Min Act: -0.1700

Data Index: 3064403 (Open Web Text)

Max Activating Token Index: 521

Text #9

Max Range: 4.0668. Min Range: -4.0668

Max Act: 4.0033. Min Act: -0.1700

Data Index: 5591469 (Open Web Text)

Max Activating Token Index: 320

Text #10

Max Range: 4.0668. Min Range: -4.0668

Max Act: 4.0283. Min Act: -0.1700

Data Index: 3057405 (Open Web Text)

Max Activating Token Index: 922

Text #11

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9289. Min Act: -0.1700

Data Index: 2732833 (Open Web Text)

Max Activating Token Index: 801

Text #12

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9531. Min Act: -0.1700

Data Index: 2862973 (Open Web Text)

Max Activating Token Index: 451

Text #13

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9459. Min Act: -0.1700

Data Index: 822138 (Open Web Text)

Max Activating Token Index: 834

Text #14

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9501. Min Act: -0.1700

Data Index: 7147817 (Open Web Text)

Max Activating Token Index: 529

Text #15

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9745. Min Act: -0.1700

Data Index: 1468753 (Open Web Text)

Max Activating Token Index: 878

Text #16

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9540. Min Act: -0.1700

Data Index: 5236852 (Open Web Text)

Max Activating Token Index: 938

Text #17

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9707. Min Act: -0.1700

Data Index: 7423678 (Open Web Text)

Max Activating Token Index: 972

Text #18

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9721. Min Act: -0.1700

Data Index: 7843761 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 4.0668. Min Range: -4.0668

Max Act: 3.9416. Min Act: -0.1700

Data Index: 4112551 (Open Web Text)

Max Activating Token Index: 487