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

Dataset: Open Web Text

Neuron 819 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: 3.8716. Min Range: -3.8716

Max Act: 3.8716. Min Act: -0.1700

Data Index: 5799172 (Open Web Text)

Max Activating Token Index: 830

Text #1

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.8363. Min Act: -0.1700

Data Index: 6484534 (Open Web Text)

Max Activating Token Index: 181

Text #2

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.8180. Min Act: -0.1700

Data Index: 2599640 (Open Web Text)

Max Activating Token Index: 88

Text #3

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.7410. Min Act: -0.1700

Data Index: 4402575 (Open Web Text)

Max Activating Token Index: 960

Text #4

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.7361. Min Act: -0.1700

Data Index: 6678573 (Open Web Text)

Max Activating Token Index: 630

Text #5

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.7728. Min Act: -0.1700

Data Index: 1571349 (Open Web Text)

Max Activating Token Index: 714

Text #6

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.7597. Min Act: -0.1700

Data Index: 2675216 (Open Web Text)

Max Activating Token Index: 484

Text #7

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.7155. Min Act: -0.1700

Data Index: 5220836 (Open Web Text)

Max Activating Token Index: 1014

Text #8

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.7037. Min Act: -0.1700

Data Index: 163465 (Open Web Text)

Max Activating Token Index: 326

Text #9

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.7064. Min Act: -0.1700

Data Index: 8776072 (Open Web Text)

Max Activating Token Index: 311

Text #10

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6906. Min Act: -0.1700

Data Index: 7311316 (Open Web Text)

Max Activating Token Index: 898

Text #11

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6868. Min Act: -0.1700

Data Index: 3743035 (Open Web Text)

Max Activating Token Index: 188

Text #12

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.7109. Min Act: -0.1700

Data Index: 8587670 (Open Web Text)

Max Activating Token Index: 614

Text #13

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6800. Min Act: -0.1700

Data Index: 8240176 (Open Web Text)

Max Activating Token Index: 193

Text #14

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.7119. Min Act: -0.1700

Data Index: 4748503 (Open Web Text)

Max Activating Token Index: 137

Text #15

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6698. Min Act: -0.1700

Data Index: 1521376 (Open Web Text)

Max Activating Token Index: 749

Text #16

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6639. Min Act: -0.1700

Data Index: 861463 (Open Web Text)

Max Activating Token Index: 618

Text #17

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6802. Min Act: -0.1700

Data Index: 5045129 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6662. Min Act: -0.1700

Data Index: 6981642 (Open Web Text)

Max Activating Token Index: 776

Text #19

Max Range: 3.8716. Min Range: -3.8716

Max Act: 3.6769. Min Act: -0.1700

Data Index: 2934560 (Open Web Text)

Max Activating Token Index: 565