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

Dataset: Open Web Text

Neuron 1561 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: 4.7852. Min Range: -4.7852

Max Act: 4.7852. Min Act: -0.1700

Data Index: 436667 (Open Web Text)

Max Activating Token Index: 385

Text #1

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.7231. Min Act: -0.1698

Data Index: 2638859 (Open Web Text)

Max Activating Token Index: 679

Text #2

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6175. Min Act: -0.1698

Data Index: 7737913 (Open Web Text)

Max Activating Token Index: 970

Text #3

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6112. Min Act: -0.1700

Data Index: 5315746 (Open Web Text)

Max Activating Token Index: 627

Text #4

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.6019. Min Act: -0.1700

Data Index: 5577349 (Open Web Text)

Max Activating Token Index: 83

Text #5

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5565. Min Act: -0.1700

Data Index: 7149263 (Open Web Text)

Max Activating Token Index: 206

Text #6

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5883. Min Act: -0.1700

Data Index: 2144038 (Open Web Text)

Max Activating Token Index: 226

Text #7

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5833. Min Act: -0.1700

Data Index: 4379035 (Open Web Text)

Max Activating Token Index: 465

Text #8

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5193. Min Act: -0.1699

Data Index: 5136998 (Open Web Text)

Max Activating Token Index: 654

Text #9

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5503. Min Act: -0.1700

Data Index: 4978567 (Open Web Text)

Max Activating Token Index: 340

Text #10

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5232. Min Act: -0.1696

Data Index: 2796160 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5652. Min Act: -0.1700

Data Index: 8186163 (Open Web Text)

Max Activating Token Index: 452

Text #12

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5395. Min Act: -0.1700

Data Index: 7378792 (Open Web Text)

Max Activating Token Index: 700

Text #13

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5062. Min Act: -0.1700

Data Index: 3038496 (Open Web Text)

Max Activating Token Index: 770

Text #14

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.4749. Min Act: -0.1700

Data Index: 4626081 (Open Web Text)

Max Activating Token Index: 775

Text #15

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5096. Min Act: -0.1700

Data Index: 8511643 (Open Web Text)

Max Activating Token Index: 196

Text #16

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5097. Min Act: -0.1700

Data Index: 5691011 (Open Web Text)

Max Activating Token Index: 571

Text #17

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.4800. Min Act: -0.1700

Data Index: 3942808 (Open Web Text)

Max Activating Token Index: 274

Text #18

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5237. Min Act: -0.1700

Data Index: 4193508 (Open Web Text)

Max Activating Token Index: 897

Text #19

Max Range: 4.7852. Min Range: -4.7852

Max Act: 4.5164. Min Act: -0.1700

Data Index: 5105112 (Open Web Text)

Max Activating Token Index: 752