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

Dataset: Open Web Text

Neuron 2428 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: 3.8260. Min Range: -3.8260

Max Act: 3.8211. Min Act: -0.1700

Data Index: 5082839 (Open Web Text)

Max Activating Token Index: 181

Text #1

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.8260. Min Act: -0.1700

Data Index: 7643830 (Open Web Text)

Max Activating Token Index: 80

Text #2

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.8099. Min Act: -0.1700

Data Index: 4674649 (Open Web Text)

Max Activating Token Index: 403

Text #3

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7931. Min Act: -0.1700

Data Index: 5185867 (Open Web Text)

Max Activating Token Index: 351

Text #4

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7880. Min Act: -0.1700

Data Index: 2293925 (Open Web Text)

Max Activating Token Index: 930

Text #5

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7544. Min Act: -0.1700

Data Index: 8572999 (Open Web Text)

Max Activating Token Index: 155

Text #6

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7525. Min Act: -0.1700

Data Index: 756977 (Open Web Text)

Max Activating Token Index: 254

Text #7

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7723. Min Act: -0.1700

Data Index: 7391355 (Open Web Text)

Max Activating Token Index: 66

Text #8

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7203. Min Act: -0.1700

Data Index: 2624203 (Open Web Text)

Max Activating Token Index: 504

Text #9

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7588. Min Act: -0.1700

Data Index: 5947413 (Open Web Text)

Max Activating Token Index: 683

Text #10

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7480. Min Act: -0.1700

Data Index: 6173728 (Open Web Text)

Max Activating Token Index: 127

Text #11

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7380. Min Act: -0.1700

Data Index: 8151020 (Open Web Text)

Max Activating Token Index: 774

Text #12

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7077. Min Act: -0.1700

Data Index: 4115748 (Open Web Text)

Max Activating Token Index: 421

Text #13

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7035. Min Act: -0.1700

Data Index: 4466466 (Open Web Text)

Max Activating Token Index: 211

Text #14

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7116. Min Act: -0.1700

Data Index: 8651871 (Open Web Text)

Max Activating Token Index: 196

Text #15

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7041. Min Act: -0.1700

Data Index: 2654256 (Open Web Text)

Max Activating Token Index: 404

Text #16

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7161. Min Act: -0.1700

Data Index: 1291909 (Open Web Text)

Max Activating Token Index: 171

Text #17

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.7121. Min Act: -0.1700

Data Index: 7713639 (Open Web Text)

Max Activating Token Index: 835

Text #18

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.6576. Min Act: -0.1700

Data Index: 2999937 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 3.8260. Min Range: -3.8260

Max Act: 3.6688. Min Act: -0.1700

Data Index: 3068506 (Open Web Text)

Max Activating Token Index: 353