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

Dataset: Open Web Text

Neuron 682 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: 3.8569. Min Range: -3.8569

Max Act: 3.8569. Min Act: -0.1700

Data Index: 4772005 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.7563. Min Act: -0.1700

Data Index: 6872084 (Open Web Text)

Max Activating Token Index: 501

Text #2

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.6249. Min Act: -0.1700

Data Index: 1629112 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.6386. Min Act: -0.1700

Data Index: 777604 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.6070. Min Act: -0.1700

Data Index: 4787506 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5935. Min Act: -0.1700

Data Index: 7140061 (Open Web Text)

Max Activating Token Index: 399

Text #6

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.6061. Min Act: -0.1700

Data Index: 7628920 (Open Web Text)

Max Activating Token Index: 919

Text #7

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5972. Min Act: -0.1700

Data Index: 6114640 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.6040. Min Act: -0.1700

Data Index: 4480387 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5817. Min Act: -0.1700

Data Index: 2134212 (Open Web Text)

Max Activating Token Index: 657

Text #10

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5809. Min Act: -0.1700

Data Index: 1967501 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5992. Min Act: -0.1700

Data Index: 1629113 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5950. Min Act: -0.1700

Data Index: 5386462 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5784. Min Act: -0.1700

Data Index: 8274192 (Open Web Text)

Max Activating Token Index: 321

Text #14

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5391. Min Act: -0.1700

Data Index: 3153255 (Open Web Text)

Max Activating Token Index: 437

Text #15

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5591. Min Act: -0.1700

Data Index: 7995381 (Open Web Text)

Max Activating Token Index: 158

Text #16

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5896. Min Act: -0.1700

Data Index: 7635978 (Open Web Text)

Max Activating Token Index: 302

Text #17

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5340. Min Act: -0.1700

Data Index: 1013674 (Open Web Text)

Max Activating Token Index: 534

Text #18

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5570. Min Act: -0.1700

Data Index: 7082938 (Open Web Text)

Max Activating Token Index: 628

Text #19

Max Range: 3.8569. Min Range: -3.8569

Max Act: 3.5561. Min Act: -0.1700

Data Index: 4853128 (Open Web Text)

Max Activating Token Index: 601