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

Dataset: Open Web Text

Neuron 1308 in Layer 5

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: 5.8873. Min Range: -5.8873

Max Act: 5.8873. Min Act: -0.1700

Data Index: 518098 (Open Web Text)

Max Activating Token Index: 387

Text #1

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.6476. Min Act: -0.1700

Data Index: 1669152 (Open Web Text)

Max Activating Token Index: 231

Text #2

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.5803. Min Act: -0.1700

Data Index: 829039 (Open Web Text)

Max Activating Token Index: 352

Text #3

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.5784. Min Act: -0.1700

Data Index: 7704927 (Open Web Text)

Max Activating Token Index: 719

Text #4

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.5798. Min Act: -0.1700

Data Index: 189719 (Open Web Text)

Max Activating Token Index: 633

Text #5

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.5659. Min Act: -0.1700

Data Index: 6936298 (Open Web Text)

Max Activating Token Index: 494

Text #6

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.6128. Min Act: -0.1700

Data Index: 4524653 (Open Web Text)

Max Activating Token Index: 483

Text #7

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.5354. Min Act: -0.1700

Data Index: 6286355 (Open Web Text)

Max Activating Token Index: 568

Text #8

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.5524. Min Act: -0.1700

Data Index: 5593760 (Open Web Text)

Max Activating Token Index: 73

Text #9

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.5183. Min Act: -0.1700

Data Index: 7334594 (Open Web Text)

Max Activating Token Index: 947

Text #10

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.4620. Min Act: -0.1700

Data Index: 4857107 (Open Web Text)

Max Activating Token Index: 561

Text #11

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.5344. Min Act: -0.1700

Data Index: 8432606 (Open Web Text)

Max Activating Token Index: 616

Text #12

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.4569. Min Act: -0.1700

Data Index: 1992446 (Open Web Text)

Max Activating Token Index: 251

Text #13

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.4799. Min Act: -0.1700

Data Index: 143608 (Open Web Text)

Max Activating Token Index: 580

Text #14

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.4719. Min Act: -0.1700

Data Index: 4516890 (Open Web Text)

Max Activating Token Index: 1007

Text #15

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.4204. Min Act: -0.1700

Data Index: 8268479 (Open Web Text)

Max Activating Token Index: 82

Text #16

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.3908. Min Act: -0.1700

Data Index: 7232329 (Open Web Text)

Max Activating Token Index: 770

Text #17

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.4142. Min Act: -0.1700

Data Index: 3863716 (Open Web Text)

Max Activating Token Index: 541

Text #18

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.4380. Min Act: -0.1700

Data Index: 6264187 (Open Web Text)

Max Activating Token Index: 763

Text #19

Max Range: 5.8873. Min Range: -5.8873

Max Act: 5.4615. Min Act: -0.1700

Data Index: 7232327 (Open Web Text)

Max Activating Token Index: 483