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

Dataset: Open Web Text

Neuron 987 in Layer 2

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: 3.4613. Min Range: -3.4613

Max Act: 3.4613. Min Act: -0.1700

Data Index: 3868556 (Open Web Text)

Max Activating Token Index: 561

Text #1

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.3841. Min Act: -0.1700

Data Index: 4076295 (Open Web Text)

Max Activating Token Index: 685

Text #2

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.2574. Min Act: -0.1700

Data Index: 2243865 (Open Web Text)

Max Activating Token Index: 846

Text #3

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.2762. Min Act: -0.1700

Data Index: 380191 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.2691. Min Act: -0.1700

Data Index: 6616453 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.2206. Min Act: -0.1700

Data Index: 8484589 (Open Web Text)

Max Activating Token Index: 109

Text #6

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.2261. Min Act: -0.1700

Data Index: 8387348 (Open Web Text)

Max Activating Token Index: 336

Text #7

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1900. Min Act: -0.1700

Data Index: 965137 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1885. Min Act: -0.1700

Data Index: 4660284 (Open Web Text)

Max Activating Token Index: 260

Text #9

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1773. Min Act: -0.1700

Data Index: 5066065 (Open Web Text)

Max Activating Token Index: 283

Text #10

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1786. Min Act: -0.1700

Data Index: 4623426 (Open Web Text)

Max Activating Token Index: 251

Text #11

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1646. Min Act: -0.1700

Data Index: 8657084 (Open Web Text)

Max Activating Token Index: 30

Text #12

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1317. Min Act: -0.1700

Data Index: 8307904 (Open Web Text)

Max Activating Token Index: 455

Text #13

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1415. Min Act: -0.1700

Data Index: 7545993 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1466. Min Act: -0.1700

Data Index: 7321422 (Open Web Text)

Max Activating Token Index: 942

Text #15

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1392. Min Act: -0.1700

Data Index: 6292035 (Open Web Text)

Max Activating Token Index: 320

Text #16

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1240. Min Act: -0.1700

Data Index: 4575465 (Open Web Text)

Max Activating Token Index: 702

Text #17

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1364. Min Act: -0.1700

Data Index: 7314902 (Open Web Text)

Max Activating Token Index: 440

Text #18

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.0985. Min Act: -0.1700

Data Index: 4012592 (Open Web Text)

Max Activating Token Index: 824

Text #19

Max Range: 3.4613. Min Range: -3.4613

Max Act: 3.1100. Min Act: -0.1700

Data Index: 2150893 (Open Web Text)

Max Activating Token Index: 112