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

Dataset: Open Web Text

Neuron 2396 in Layer 0

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: 5.4487. Min Range: -5.4487

Max Act: 5.4487. Min Act: -0.1700

Data Index: 5941061 (Open Web Text)

Max Activating Token Index: 696

Text #1

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.3659. Min Act: -0.1699

Data Index: 1643889 (Open Web Text)

Max Activating Token Index: 945

Text #2

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.3197. Min Act: -0.1698

Data Index: 836092 (Open Web Text)

Max Activating Token Index: 753

Text #3

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.2871. Min Act: -0.1700

Data Index: 3563919 (Open Web Text)

Max Activating Token Index: 53

Text #4

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.2535. Min Act: -0.1698

Data Index: 3563922 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.2300. Min Act: -0.1700

Data Index: 5941069 (Open Web Text)

Max Activating Token Index: 807

Text #6

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.1573. Min Act: -0.1700

Data Index: 3563921 (Open Web Text)

Max Activating Token Index: 779

Text #7

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.1885. Min Act: -0.1700

Data Index: 6321173 (Open Web Text)

Max Activating Token Index: 213

Text #8

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.1762. Min Act: -0.1700

Data Index: 2900778 (Open Web Text)

Max Activating Token Index: 585

Text #9

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.1449. Min Act: -0.1700

Data Index: 954801 (Open Web Text)

Max Activating Token Index: 155

Text #10

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.1386. Min Act: -0.1700

Data Index: 2142797 (Open Web Text)

Max Activating Token Index: 634

Text #11

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.1133. Min Act: -0.1700

Data Index: 5341079 (Open Web Text)

Max Activating Token Index: 688

Text #12

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.1217. Min Act: -0.1700

Data Index: 6373065 (Open Web Text)

Max Activating Token Index: 62

Text #13

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.0946. Min Act: -0.1699

Data Index: 654565 (Open Web Text)

Max Activating Token Index: 773

Text #14

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.0864. Min Act: -0.1700

Data Index: 8784572 (Open Web Text)

Max Activating Token Index: 632

Text #15

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.0800. Min Act: -0.1700

Data Index: 8143692 (Open Web Text)

Max Activating Token Index: 365

Text #16

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.0934. Min Act: -0.1698

Data Index: 6725306 (Open Web Text)

Max Activating Token Index: 689

Text #17

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.0606. Min Act: -0.1698

Data Index: 8143679 (Open Web Text)

Max Activating Token Index: 789

Text #18

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.0477. Min Act: -0.1700

Data Index: 7569484 (Open Web Text)

Max Activating Token Index: 567

Text #19

Max Range: 5.4487. Min Range: -5.4487

Max Act: 5.0539. Min Act: -0.1700

Data Index: 5625675 (Open Web Text)

Max Activating Token Index: 15