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

Dataset: Open Web Text

Neuron 2343 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: 3.5144. Min Range: -3.5144

Max Act: 3.5144. Min Act: -0.1700

Data Index: 378652 (Open Web Text)

Max Activating Token Index: 46

Text #1

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4840. Min Act: -0.1700

Data Index: 1745374 (Open Web Text)

Max Activating Token Index: 1010

Text #2

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4980. Min Act: -0.1700

Data Index: 493204 (Open Web Text)

Max Activating Token Index: 581

Text #3

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4454. Min Act: -0.1700

Data Index: 6331117 (Open Web Text)

Max Activating Token Index: 995

Text #4

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4418. Min Act: -0.1700

Data Index: 7373294 (Open Web Text)

Max Activating Token Index: 424

Text #5

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3741. Min Act: -0.1700

Data Index: 1579443 (Open Web Text)

Max Activating Token Index: 773

Text #6

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3898. Min Act: -0.1700

Data Index: 1174337 (Open Web Text)

Max Activating Token Index: 115

Text #7

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3703. Min Act: -0.1700

Data Index: 7105663 (Open Web Text)

Max Activating Token Index: 799

Text #8

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3630. Min Act: -0.1700

Data Index: 95562 (Open Web Text)

Max Activating Token Index: 728

Text #9

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3783. Min Act: -0.1700

Data Index: 7953080 (Open Web Text)

Max Activating Token Index: 782

Text #10

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3642. Min Act: -0.1700

Data Index: 3271066 (Open Web Text)

Max Activating Token Index: 298

Text #11

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3454. Min Act: -0.1700

Data Index: 5618699 (Open Web Text)

Max Activating Token Index: 168

Text #12

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3382. Min Act: -0.1700

Data Index: 3958292 (Open Web Text)

Max Activating Token Index: 806

Text #13

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3610. Min Act: -0.1700

Data Index: 6986622 (Open Web Text)

Max Activating Token Index: 641

Text #14

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3243. Min Act: -0.1700

Data Index: 6773861 (Open Web Text)

Max Activating Token Index: 134

Text #15

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3162. Min Act: -0.1700

Data Index: 1211231 (Open Web Text)

Max Activating Token Index: 912

Text #16

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3112. Min Act: -0.1700

Data Index: 1468191 (Open Web Text)

Max Activating Token Index: 994

Text #17

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3181. Min Act: -0.1700

Data Index: 1517413 (Open Web Text)

Max Activating Token Index: 606

Text #18

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3080. Min Act: -0.1700

Data Index: 2726297 (Open Web Text)

Max Activating Token Index: 572

Text #19

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3182. Min Act: -0.1700

Data Index: 917560 (Open Web Text)

Max Activating Token Index: 260