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

Dataset: Open Web Text

Neuron 679 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: 3.6622. Min Range: -3.6622

Max Act: 3.6622. Min Act: -0.1700

Data Index: 4787307 (Open Web Text)

Max Activating Token Index: 322

Text #1

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.6512. Min Act: -0.1700

Data Index: 1439410 (Open Web Text)

Max Activating Token Index: 552

Text #2

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.6018. Min Act: -0.1700

Data Index: 202991 (Open Web Text)

Max Activating Token Index: 519

Text #3

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.5665. Min Act: -0.1700

Data Index: 6218181 (Open Web Text)

Max Activating Token Index: 535

Text #4

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.5734. Min Act: -0.1700

Data Index: 5722185 (Open Web Text)

Max Activating Token Index: 349

Text #5

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.5222. Min Act: -0.1700

Data Index: 2167150 (Open Web Text)

Max Activating Token Index: 788

Text #6

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.5246. Min Act: -0.1700

Data Index: 225315 (Open Web Text)

Max Activating Token Index: 624

Text #7

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.5147. Min Act: -0.1700

Data Index: 7844202 (Open Web Text)

Max Activating Token Index: 850

Text #8

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.5067. Min Act: -0.1700

Data Index: 136695 (Open Web Text)

Max Activating Token Index: 839

Text #9

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.4652. Min Act: -0.1700

Data Index: 4467888 (Open Web Text)

Max Activating Token Index: 877

Text #10

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.4921. Min Act: -0.1700

Data Index: 8770157 (Open Web Text)

Max Activating Token Index: 147

Text #11

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.4708. Min Act: -0.1700

Data Index: 5769673 (Open Web Text)

Max Activating Token Index: 454

Text #12

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.4931. Min Act: -0.1700

Data Index: 7079584 (Open Web Text)

Max Activating Token Index: 768

Text #13

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.4458. Min Act: -0.1700

Data Index: 6689043 (Open Web Text)

Max Activating Token Index: 166

Text #14

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.4760. Min Act: -0.1700

Data Index: 5136912 (Open Web Text)

Max Activating Token Index: 483

Text #15

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.4653. Min Act: -0.1700

Data Index: 7020624 (Open Web Text)

Max Activating Token Index: 287

Text #16

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.4879. Min Act: -0.1700

Data Index: 776874 (Open Web Text)

Max Activating Token Index: 523

Text #17

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.4633. Min Act: -0.1700

Data Index: 4408247 (Open Web Text)

Max Activating Token Index: 223

Text #18

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.4344. Min Act: -0.1700

Data Index: 2676738 (Open Web Text)

Max Activating Token Index: 809

Text #19

Max Range: 3.6622. Min Range: -3.6622

Max Act: 3.4542. Min Act: -0.1700

Data Index: 3016053 (Open Web Text)

Max Activating Token Index: 705