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

Dataset: Open Web Text

Neuron 2984 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: 3.2291. Min Range: -3.2291

Max Act: 3.2291. Min Act: -0.1700

Data Index: 3912694 (Open Web Text)

Max Activating Token Index: 650

Text #1

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.1509. Min Act: -0.1700

Data Index: 4838812 (Open Web Text)

Max Activating Token Index: 757

Text #2

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.1350. Min Act: -0.1700

Data Index: 6202064 (Open Web Text)

Max Activating Token Index: 355

Text #3

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.1492. Min Act: -0.1700

Data Index: 7900110 (Open Web Text)

Max Activating Token Index: 165

Text #4

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.1064. Min Act: -0.1700

Data Index: 7782447 (Open Web Text)

Max Activating Token Index: 705

Text #5

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0849. Min Act: -0.1700

Data Index: 3707244 (Open Web Text)

Max Activating Token Index: 485

Text #6

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0911. Min Act: -0.1700

Data Index: 7713119 (Open Web Text)

Max Activating Token Index: 185

Text #7

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0972. Min Act: -0.1700

Data Index: 4838813 (Open Web Text)

Max Activating Token Index: 283

Text #8

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0722. Min Act: -0.1700

Data Index: 1054427 (Open Web Text)

Max Activating Token Index: 75

Text #9

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0890. Min Act: -0.1700

Data Index: 7939531 (Open Web Text)

Max Activating Token Index: 230

Text #10

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0853. Min Act: -0.1700

Data Index: 3792471 (Open Web Text)

Max Activating Token Index: 666

Text #11

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0758. Min Act: -0.1700

Data Index: 2952048 (Open Web Text)

Max Activating Token Index: 254

Text #12

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0588. Min Act: -0.1700

Data Index: 4773677 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0616. Min Act: -0.1700

Data Index: 7879762 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0715. Min Act: -0.1700

Data Index: 3214467 (Open Web Text)

Max Activating Token Index: 508

Text #15

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0686. Min Act: -0.1700

Data Index: 1361039 (Open Web Text)

Max Activating Token Index: 1000

Text #16

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0260. Min Act: -0.1700

Data Index: 8266955 (Open Web Text)

Max Activating Token Index: 836

Text #17

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0416. Min Act: -0.1700

Data Index: 1310673 (Open Web Text)

Max Activating Token Index: 317

Text #18

Max Range: 3.2291. Min Range: -3.2291

Max Act: 3.0142. Min Act: -0.1700

Data Index: 3669946 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 3.2291. Min Range: -3.2291

Max Act: 2.9972. Min Act: -0.1700

Data Index: 1038861 (Open Web Text)

Max Activating Token Index: 206