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

Dataset: Open Web Text

Neuron 1495 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: 3.6812. Min Range: -3.6812

Max Act: 3.6812. Min Act: -0.1700

Data Index: 4319516 (Open Web Text)

Max Activating Token Index: 97

Text #1

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.5486. Min Act: -0.1700

Data Index: 6133240 (Open Web Text)

Max Activating Token Index: 781

Text #2

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.5537. Min Act: -0.1700

Data Index: 6075387 (Open Web Text)

Max Activating Token Index: 478

Text #3

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.5275. Min Act: -0.1700

Data Index: 7388535 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.5020. Min Act: -0.1700

Data Index: 3760346 (Open Web Text)

Max Activating Token Index: 145

Text #5

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.5039. Min Act: -0.1700

Data Index: 3914117 (Open Web Text)

Max Activating Token Index: 99

Text #6

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4932. Min Act: -0.1700

Data Index: 995555 (Open Web Text)

Max Activating Token Index: 362

Text #7

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4539. Min Act: -0.1700

Data Index: 3515633 (Open Web Text)

Max Activating Token Index: 491

Text #8

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4696. Min Act: -0.1700

Data Index: 4475010 (Open Web Text)

Max Activating Token Index: 941

Text #9

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4561. Min Act: -0.1700

Data Index: 1205233 (Open Web Text)

Max Activating Token Index: 818

Text #10

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4892. Min Act: -0.1700

Data Index: 5369510 (Open Web Text)

Max Activating Token Index: 583

Text #11

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4590. Min Act: -0.1700

Data Index: 2424242 (Open Web Text)

Max Activating Token Index: 966

Text #12

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4520. Min Act: -0.1700

Data Index: 2841461 (Open Web Text)

Max Activating Token Index: 655

Text #13

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4819. Min Act: -0.1700

Data Index: 7825114 (Open Web Text)

Max Activating Token Index: 822

Text #14

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4692. Min Act: -0.1700

Data Index: 3820091 (Open Web Text)

Max Activating Token Index: 214

Text #15

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4765. Min Act: -0.1700

Data Index: 5090806 (Open Web Text)

Max Activating Token Index: 906

Text #16

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4532. Min Act: -0.1700

Data Index: 1082571 (Open Web Text)

Max Activating Token Index: 893

Text #17

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4644. Min Act: -0.1700

Data Index: 1082572 (Open Web Text)

Max Activating Token Index: 141

Text #18

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4667. Min Act: -0.1700

Data Index: 7329757 (Open Web Text)

Max Activating Token Index: 718

Text #19

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.4164. Min Act: -0.1700

Data Index: 2852903 (Open Web Text)

Max Activating Token Index: 879