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

Dataset: Open Web Text

Neuron 688 in Layer 4

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: 3.7816. Min Range: -3.7816

Max Act: 3.7753. Min Act: -0.1700

Data Index: 1359280 (Open Web Text)

Max Activating Token Index: 922

Text #1

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7785. Min Act: -0.1700

Data Index: 3777382 (Open Web Text)

Max Activating Token Index: 781

Text #2

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7752. Min Act: -0.1700

Data Index: 1670487 (Open Web Text)

Max Activating Token Index: 479

Text #3

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7816. Min Act: -0.1700

Data Index: 4496548 (Open Web Text)

Max Activating Token Index: 474

Text #4

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7174. Min Act: -0.1700

Data Index: 1741110 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7301. Min Act: -0.1700

Data Index: 2330825 (Open Web Text)

Max Activating Token Index: 811

Text #6

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7150. Min Act: -0.1700

Data Index: 8249210 (Open Web Text)

Max Activating Token Index: 394

Text #7

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7291. Min Act: -0.1700

Data Index: 3296606 (Open Web Text)

Max Activating Token Index: 948

Text #8

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7032. Min Act: -0.1700

Data Index: 8257762 (Open Web Text)

Max Activating Token Index: 588

Text #9

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6926. Min Act: -0.1700

Data Index: 1951100 (Open Web Text)

Max Activating Token Index: 289

Text #10

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.7249. Min Act: -0.1700

Data Index: 6640763 (Open Web Text)

Max Activating Token Index: 564

Text #11

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6968. Min Act: -0.1700

Data Index: 8623266 (Open Web Text)

Max Activating Token Index: 750

Text #12

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6447. Min Act: -0.1700

Data Index: 7774072 (Open Web Text)

Max Activating Token Index: 99

Text #13

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6710. Min Act: -0.1700

Data Index: 8019592 (Open Web Text)

Max Activating Token Index: 378

Text #14

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6546. Min Act: -0.1700

Data Index: 3777383 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6625. Min Act: -0.1700

Data Index: 8674790 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6597. Min Act: -0.1700

Data Index: 6970589 (Open Web Text)

Max Activating Token Index: 402

Text #17

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6833. Min Act: -0.1700

Data Index: 2195794 (Open Web Text)

Max Activating Token Index: 400

Text #18

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6709. Min Act: -0.1700

Data Index: 409012 (Open Web Text)

Max Activating Token Index: 622

Text #19

Max Range: 3.7816. Min Range: -3.7816

Max Act: 3.6385. Min Act: -0.1700

Data Index: 5472281 (Open Web Text)

Max Activating Token Index: 682