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

Dataset: Open Web Text

Neuron 682 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: 4.1125. Min Range: -4.1125

Max Act: 4.1125. Min Act: -0.1700

Data Index: 5447623 (Open Web Text)

Max Activating Token Index: 596

Text #1

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.9616. Min Act: -0.1700

Data Index: 455061 (Open Web Text)

Max Activating Token Index: 21

Text #2

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8811. Min Act: -0.1700

Data Index: 660843 (Open Web Text)

Max Activating Token Index: 416

Text #3

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.9014. Min Act: -0.1700

Data Index: 4496784 (Open Web Text)

Max Activating Token Index: 52

Text #4

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8916. Min Act: -0.1700

Data Index: 5528838 (Open Web Text)

Max Activating Token Index: 224

Text #5

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8419. Min Act: -0.1700

Data Index: 6031057 (Open Web Text)

Max Activating Token Index: 706

Text #6

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8768. Min Act: -0.1700

Data Index: 6554710 (Open Web Text)

Max Activating Token Index: 480

Text #7

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8489. Min Act: -0.1700

Data Index: 2172358 (Open Web Text)

Max Activating Token Index: 19

Text #8

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8500. Min Act: -0.1700

Data Index: 6554712 (Open Web Text)

Max Activating Token Index: 665

Text #9

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8861. Min Act: -0.1700

Data Index: 5387505 (Open Web Text)

Max Activating Token Index: 628

Text #10

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8458. Min Act: -0.1700

Data Index: 7062471 (Open Web Text)

Max Activating Token Index: 28

Text #11

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8543. Min Act: -0.1700

Data Index: 5951837 (Open Web Text)

Max Activating Token Index: 959

Text #12

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8369. Min Act: -0.1700

Data Index: 6174622 (Open Web Text)

Max Activating Token Index: 523

Text #13

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8264. Min Act: -0.1700

Data Index: 6587705 (Open Web Text)

Max Activating Token Index: 219

Text #14

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8368. Min Act: -0.1700

Data Index: 431860 (Open Web Text)

Max Activating Token Index: 419

Text #15

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.7996. Min Act: -0.1700

Data Index: 7050997 (Open Web Text)

Max Activating Token Index: 919

Text #16

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.7880. Min Act: -0.1700

Data Index: 6007773 (Open Web Text)

Max Activating Token Index: 340

Text #17

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8173. Min Act: -0.1700

Data Index: 7830968 (Open Web Text)

Max Activating Token Index: 740

Text #18

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.7703. Min Act: -0.1700

Data Index: 4371441 (Open Web Text)

Max Activating Token Index: 739

Text #19

Max Range: 4.1125. Min Range: -4.1125

Max Act: 3.8036. Min Act: -0.1700

Data Index: 3696204 (Open Web Text)

Max Activating Token Index: 909