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

Dataset: Open Web Text

Neuron 2467 in Layer 1

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: 4.5830. Min Range: -4.5830

Max Act: 4.5830. Min Act: -0.1700

Data Index: 5917768 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.4793. Min Act: -0.1700

Data Index: 1070662 (Open Web Text)

Max Activating Token Index: 583

Text #2

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.4686. Min Act: -0.1700

Data Index: 2468047 (Open Web Text)

Max Activating Token Index: 612

Text #3

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.4923. Min Act: -0.1700

Data Index: 4674526 (Open Web Text)

Max Activating Token Index: 139

Text #4

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.4679. Min Act: -0.1700

Data Index: 4987628 (Open Web Text)

Max Activating Token Index: 337

Text #5

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.4410. Min Act: -0.1700

Data Index: 5201214 (Open Web Text)

Max Activating Token Index: 253

Text #6

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.4227. Min Act: -0.1700

Data Index: 1326135 (Open Web Text)

Max Activating Token Index: 657

Text #7

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.3926. Min Act: -0.1700

Data Index: 7292392 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.4103. Min Act: -0.1700

Data Index: 3762804 (Open Web Text)

Max Activating Token Index: 585

Text #9

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.4198. Min Act: -0.1700

Data Index: 6979406 (Open Web Text)

Max Activating Token Index: 443

Text #10

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.4095. Min Act: -0.1700

Data Index: 8580725 (Open Web Text)

Max Activating Token Index: 273

Text #11

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.4155. Min Act: -0.1700

Data Index: 4460838 (Open Web Text)

Max Activating Token Index: 594

Text #12

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.3780. Min Act: -0.1700

Data Index: 2761275 (Open Web Text)

Max Activating Token Index: 153

Text #13

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.3757. Min Act: -0.1700

Data Index: 5448328 (Open Web Text)

Max Activating Token Index: 596

Text #14

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.3619. Min Act: -0.1700

Data Index: 5481055 (Open Web Text)

Max Activating Token Index: 713

Text #15

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.3628. Min Act: -0.1700

Data Index: 875433 (Open Web Text)

Max Activating Token Index: 395

Text #16

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.3796. Min Act: -0.1700

Data Index: 603930 (Open Web Text)

Max Activating Token Index: 1012

Text #17

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.3776. Min Act: -0.1700

Data Index: 296509 (Open Web Text)

Max Activating Token Index: 162

Text #18

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.3901. Min Act: -0.1700

Data Index: 1122742 (Open Web Text)

Max Activating Token Index: 689

Text #19

Max Range: 4.5830. Min Range: -4.5830

Max Act: 4.3704. Min Act: -0.1700

Data Index: 2494755 (Open Web Text)

Max Activating Token Index: 994