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

Dataset: Open Web Text

Neuron 2799 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: 3.0367. Min Range: -3.0367

Max Act: 3.0367. Min Act: -0.1700

Data Index: 3617629 (Open Web Text)

Max Activating Token Index: 588

Text #1

Max Range: 3.0367. Min Range: -3.0367

Max Act: 3.0079. Min Act: -0.1700

Data Index: 8820393 (Open Web Text)

Max Activating Token Index: 649

Text #2

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9934. Min Act: -0.1700

Data Index: 8785158 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9752. Min Act: -0.1700

Data Index: 4793141 (Open Web Text)

Max Activating Token Index: 712

Text #4

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9525. Min Act: -0.1700

Data Index: 8257344 (Open Web Text)

Max Activating Token Index: 397

Text #5

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9548. Min Act: -0.1700

Data Index: 6907799 (Open Web Text)

Max Activating Token Index: 811

Text #6

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9515. Min Act: -0.1700

Data Index: 7562246 (Open Web Text)

Max Activating Token Index: 129

Text #7

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9375. Min Act: -0.1700

Data Index: 373951 (Open Web Text)

Max Activating Token Index: 681

Text #8

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9395. Min Act: -0.1700

Data Index: 3955103 (Open Web Text)

Max Activating Token Index: 850

Text #9

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9236. Min Act: -0.1700

Data Index: 1095447 (Open Web Text)

Max Activating Token Index: 682

Text #10

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9188. Min Act: -0.1700

Data Index: 3598407 (Open Web Text)

Max Activating Token Index: 40

Text #11

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9145. Min Act: -0.1700

Data Index: 7977273 (Open Web Text)

Max Activating Token Index: 832

Text #12

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9050. Min Act: -0.1700

Data Index: 1618697 (Open Web Text)

Max Activating Token Index: 188

Text #13

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.8905. Min Act: -0.1700

Data Index: 1174879 (Open Web Text)

Max Activating Token Index: 508

Text #14

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.8922. Min Act: -0.1700

Data Index: 7839828 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.8917. Min Act: -0.1700

Data Index: 6853266 (Open Web Text)

Max Activating Token Index: 487

Text #16

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.8986. Min Act: -0.1700

Data Index: 2270074 (Open Web Text)

Max Activating Token Index: 648

Text #17

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9070. Min Act: -0.1700

Data Index: 5311509 (Open Web Text)

Max Activating Token Index: 838

Text #18

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9184. Min Act: -0.1700

Data Index: 8419319 (Open Web Text)

Max Activating Token Index: 296

Text #19

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9013. Min Act: -0.1700

Data Index: 1389983 (Open Web Text)

Max Activating Token Index: 891