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

Dataset: Open Web Text

Neuron 971 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: 3.8073. Min Range: -3.8073

Max Act: 3.8073. Min Act: -0.1700

Data Index: 6646622 (Open Web Text)

Max Activating Token Index: 883

Text #1

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.7445. Min Act: -0.1700

Data Index: 5041452 (Open Web Text)

Max Activating Token Index: 700

Text #2

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.7757. Min Act: -0.1700

Data Index: 7652716 (Open Web Text)

Max Activating Token Index: 130

Text #3

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.7205. Min Act: -0.1700

Data Index: 6374222 (Open Web Text)

Max Activating Token Index: 280

Text #4

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.6857. Min Act: -0.1700

Data Index: 1340709 (Open Web Text)

Max Activating Token Index: 766

Text #5

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.7032. Min Act: -0.1700

Data Index: 7286114 (Open Web Text)

Max Activating Token Index: 322

Text #6

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.6968. Min Act: -0.1700

Data Index: 8653710 (Open Web Text)

Max Activating Token Index: 236

Text #7

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.6752. Min Act: -0.1700

Data Index: 4619803 (Open Web Text)

Max Activating Token Index: 654

Text #8

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.6710. Min Act: -0.1700

Data Index: 236777 (Open Web Text)

Max Activating Token Index: 945

Text #9

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.6743. Min Act: -0.1700

Data Index: 6349515 (Open Web Text)

Max Activating Token Index: 377

Text #10

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.6076. Min Act: -0.1700

Data Index: 5858398 (Open Web Text)

Max Activating Token Index: 498

Text #11

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.6358. Min Act: -0.1700

Data Index: 4739505 (Open Web Text)

Max Activating Token Index: 128

Text #12

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.6371. Min Act: -0.1700

Data Index: 5186819 (Open Web Text)

Max Activating Token Index: 261

Text #13

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.6056. Min Act: -0.1700

Data Index: 6374128 (Open Web Text)

Max Activating Token Index: 680

Text #14

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.6099. Min Act: -0.1700

Data Index: 851826 (Open Web Text)

Max Activating Token Index: 314

Text #15

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.6017. Min Act: -0.1700

Data Index: 2755201 (Open Web Text)

Max Activating Token Index: 393

Text #16

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.6047. Min Act: -0.1700

Data Index: 4389463 (Open Web Text)

Max Activating Token Index: 410

Text #17

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.5775. Min Act: -0.1700

Data Index: 8220481 (Open Web Text)

Max Activating Token Index: 416

Text #18

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.5849. Min Act: -0.1700

Data Index: 3944639 (Open Web Text)

Max Activating Token Index: 120

Text #19

Max Range: 3.8073. Min Range: -3.8073

Max Act: 3.5787. Min Act: -0.1700

Data Index: 2653460 (Open Web Text)

Max Activating Token Index: 617