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

Dataset: Open Web Text

Neuron 856 in Layer 6

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: 4.6429. Min Range: -4.6429

Max Act: 4.6429. Min Act: -0.1700

Data Index: 8185746 (Open Web Text)

Max Activating Token Index: 903

Text #1

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.5902. Min Act: -0.1700

Data Index: 7577409 (Open Web Text)

Max Activating Token Index: 1007

Text #2

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.6259. Min Act: -0.1700

Data Index: 2804326 (Open Web Text)

Max Activating Token Index: 921

Text #3

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.6100. Min Act: -0.1700

Data Index: 850645 (Open Web Text)

Max Activating Token Index: 92

Text #4

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.5691. Min Act: -0.1700

Data Index: 4030362 (Open Web Text)

Max Activating Token Index: 592

Text #5

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.5134. Min Act: -0.1700

Data Index: 5038176 (Open Web Text)

Max Activating Token Index: 973

Text #6

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.4878. Min Act: -0.1700

Data Index: 1807009 (Open Web Text)

Max Activating Token Index: 283

Text #7

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.4192. Min Act: -0.1700

Data Index: 6467657 (Open Web Text)

Max Activating Token Index: 891

Text #8

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.4422. Min Act: -0.1700

Data Index: 5382766 (Open Web Text)

Max Activating Token Index: 153

Text #9

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.4417. Min Act: -0.1700

Data Index: 8525919 (Open Web Text)

Max Activating Token Index: 853

Text #10

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.4338. Min Act: -0.1700

Data Index: 4960872 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.4509. Min Act: -0.1700

Data Index: 5945839 (Open Web Text)

Max Activating Token Index: 569

Text #12

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.4242. Min Act: -0.1700

Data Index: 4008314 (Open Web Text)

Max Activating Token Index: 585

Text #13

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.4061. Min Act: -0.1700

Data Index: 7848792 (Open Web Text)

Max Activating Token Index: 342

Text #14

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.3693. Min Act: -0.1700

Data Index: 1478667 (Open Web Text)

Max Activating Token Index: 993

Text #15

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.3718. Min Act: -0.1700

Data Index: 6726651 (Open Web Text)

Max Activating Token Index: 751

Text #16

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.4091. Min Act: -0.1700

Data Index: 6236077 (Open Web Text)

Max Activating Token Index: 217

Text #17

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.3955. Min Act: -0.1700

Data Index: 985480 (Open Web Text)

Max Activating Token Index: 391

Text #18

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.4058. Min Act: -0.1700

Data Index: 5975119 (Open Web Text)

Max Activating Token Index: 662

Text #19

Max Range: 4.6429. Min Range: -4.6429

Max Act: 4.3211. Min Act: -0.1700

Data Index: 4289034 (Open Web Text)

Max Activating Token Index: 864