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

Dataset: Open Web Text

Neuron 642 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: 4.5181. Min Range: -4.5181

Max Act: 4.5181. Min Act: -0.1700

Data Index: 5988576 (Open Web Text)

Max Activating Token Index: 327

Text #1

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.4364. Min Act: -0.1700

Data Index: 5539120 (Open Web Text)

Max Activating Token Index: 756

Text #2

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.4087. Min Act: -0.1700

Data Index: 7852994 (Open Web Text)

Max Activating Token Index: 562

Text #3

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.3705. Min Act: -0.1700

Data Index: 2298380 (Open Web Text)

Max Activating Token Index: 777

Text #4

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.4008. Min Act: -0.1700

Data Index: 7195960 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.3558. Min Act: -0.1700

Data Index: 5020434 (Open Web Text)

Max Activating Token Index: 411

Text #6

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.3003. Min Act: -0.1700

Data Index: 2643182 (Open Web Text)

Max Activating Token Index: 715

Text #7

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.3082. Min Act: -0.1700

Data Index: 5249771 (Open Web Text)

Max Activating Token Index: 357

Text #8

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.3113. Min Act: -0.1700

Data Index: 240074 (Open Web Text)

Max Activating Token Index: 307

Text #9

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.3469. Min Act: -0.1700

Data Index: 1489786 (Open Web Text)

Max Activating Token Index: 874

Text #10

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.3043. Min Act: -0.1700

Data Index: 3701992 (Open Web Text)

Max Activating Token Index: 439

Text #11

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.3215. Min Act: -0.1700

Data Index: 7005227 (Open Web Text)

Max Activating Token Index: 831

Text #12

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.3345. Min Act: -0.1700

Data Index: 6176502 (Open Web Text)

Max Activating Token Index: 403

Text #13

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.3037. Min Act: -0.1700

Data Index: 4493428 (Open Web Text)

Max Activating Token Index: 875

Text #14

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.2925. Min Act: -0.1700

Data Index: 648192 (Open Web Text)

Max Activating Token Index: 217

Text #15

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.2788. Min Act: -0.1700

Data Index: 4619168 (Open Web Text)

Max Activating Token Index: 455

Text #16

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.2740. Min Act: -0.1700

Data Index: 4291888 (Open Web Text)

Max Activating Token Index: 451

Text #17

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.2649. Min Act: -0.1700

Data Index: 3627666 (Open Web Text)

Max Activating Token Index: 769

Text #18

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.2904. Min Act: -0.1700

Data Index: 5408156 (Open Web Text)

Max Activating Token Index: 873

Text #19

Max Range: 4.5181. Min Range: -4.5181

Max Act: 4.2755. Min Act: -0.1700

Data Index: 8001748 (Open Web Text)

Max Activating Token Index: 790