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

Dataset: Open Web Text

Neuron 861 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: 7.8370. Min Range: -7.8370

Max Act: 7.8370. Min Act: -0.1700

Data Index: 7095348 (Open Web Text)

Max Activating Token Index: 644

Text #1

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.7551. Min Act: -0.1700

Data Index: 3490041 (Open Web Text)

Max Activating Token Index: 466

Text #2

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.6549. Min Act: -0.1700

Data Index: 4549899 (Open Web Text)

Max Activating Token Index: 46

Text #3

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.6640. Min Act: -0.1700

Data Index: 5553448 (Open Web Text)

Max Activating Token Index: 115

Text #4

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.6362. Min Act: -0.1700

Data Index: 6642716 (Open Web Text)

Max Activating Token Index: 772

Text #5

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.5935. Min Act: -0.1700

Data Index: 792673 (Open Web Text)

Max Activating Token Index: 440

Text #6

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.5829. Min Act: -0.1700

Data Index: 6492797 (Open Web Text)

Max Activating Token Index: 476

Text #7

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.5416. Min Act: -0.1700

Data Index: 2732075 (Open Web Text)

Max Activating Token Index: 991

Text #8

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.4934. Min Act: -0.1700

Data Index: 2086344 (Open Web Text)

Max Activating Token Index: 544

Text #9

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.5100. Min Act: -0.1700

Data Index: 6104245 (Open Web Text)

Max Activating Token Index: 391

Text #10

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.4871. Min Act: -0.1700

Data Index: 5246978 (Open Web Text)

Max Activating Token Index: 564

Text #11

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.4544. Min Act: -0.1700

Data Index: 7332825 (Open Web Text)

Max Activating Token Index: 834

Text #12

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.4408. Min Act: -0.1700

Data Index: 5356964 (Open Web Text)

Max Activating Token Index: 640

Text #13

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.4186. Min Act: -0.1700

Data Index: 7748776 (Open Web Text)

Max Activating Token Index: 502

Text #14

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.3827. Min Act: -0.1700

Data Index: 7834124 (Open Web Text)

Max Activating Token Index: 827

Text #15

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.3933. Min Act: -0.1700

Data Index: 240362 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.3997. Min Act: -0.1700

Data Index: 3707261 (Open Web Text)

Max Activating Token Index: 1016

Text #17

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.4102. Min Act: -0.1700

Data Index: 5988666 (Open Web Text)

Max Activating Token Index: 53

Text #18

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.4156. Min Act: -0.1700

Data Index: 2127973 (Open Web Text)

Max Activating Token Index: 993

Text #19

Max Range: 7.8370. Min Range: -7.8370

Max Act: 7.3201. Min Act: -0.1700

Data Index: 5196670 (Open Web Text)

Max Activating Token Index: 677