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

Dataset: Open Web Text

Neuron 1091 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: 3.1779. Min Range: -3.1779

Max Act: 3.1779. Min Act: -0.1700

Data Index: 6936896 (Open Web Text)

Max Activating Token Index: 57

Text #1

Max Range: 3.1779. Min Range: -3.1779

Max Act: 3.1420. Min Act: -0.1700

Data Index: 190424 (Open Web Text)

Max Activating Token Index: 29

Text #2

Max Range: 3.1779. Min Range: -3.1779

Max Act: 3.1377. Min Act: -0.1700

Data Index: 6936891 (Open Web Text)

Max Activating Token Index: 895

Text #3

Max Range: 3.1779. Min Range: -3.1779

Max Act: 3.1127. Min Act: -0.1700

Data Index: 2339492 (Open Web Text)

Max Activating Token Index: 32

Text #4

Max Range: 3.1779. Min Range: -3.1779

Max Act: 3.1103. Min Act: -0.1700

Data Index: 6936895 (Open Web Text)

Max Activating Token Index: 464

Text #5

Max Range: 3.1779. Min Range: -3.1779

Max Act: 3.0913. Min Act: -0.1700

Data Index: 190431 (Open Web Text)

Max Activating Token Index: 44

Text #6

Max Range: 3.1779. Min Range: -3.1779

Max Act: 3.0663. Min Act: -0.1700

Data Index: 190433 (Open Web Text)

Max Activating Token Index: 136

Text #7

Max Range: 3.1779. Min Range: -3.1779

Max Act: 3.0194. Min Act: -0.1700

Data Index: 4811855 (Open Web Text)

Max Activating Token Index: 268

Text #8

Max Range: 3.1779. Min Range: -3.1779

Max Act: 3.0154. Min Act: -0.1700

Data Index: 190432 (Open Web Text)

Max Activating Token Index: 139

Text #9

Max Range: 3.1779. Min Range: -3.1779

Max Act: 3.0000. Min Act: -0.1700

Data Index: 7588437 (Open Web Text)

Max Activating Token Index: 158

Text #10

Max Range: 3.1779. Min Range: -3.1779

Max Act: 2.9993. Min Act: -0.1700

Data Index: 6437417 (Open Web Text)

Max Activating Token Index: 96

Text #11

Max Range: 3.1779. Min Range: -3.1779

Max Act: 2.9857. Min Act: -0.1700

Data Index: 5028843 (Open Web Text)

Max Activating Token Index: 648

Text #12

Max Range: 3.1779. Min Range: -3.1779

Max Act: 2.9771. Min Act: -0.1700

Data Index: 3227834 (Open Web Text)

Max Activating Token Index: 96

Text #13

Max Range: 3.1779. Min Range: -3.1779

Max Act: 2.9838. Min Act: -0.1700

Data Index: 4811852 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 3.1779. Min Range: -3.1779

Max Act: 2.9631. Min Act: -0.1700

Data Index: 5028840 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 3.1779. Min Range: -3.1779

Max Act: 2.9823. Min Act: -0.1700

Data Index: 6936893 (Open Web Text)

Max Activating Token Index: 511

Text #16

Max Range: 3.1779. Min Range: -3.1779

Max Act: 2.9811. Min Act: -0.1700

Data Index: 190422 (Open Web Text)

Max Activating Token Index: 89

Text #17

Max Range: 3.1779. Min Range: -3.1779

Max Act: 2.9392. Min Act: -0.1700

Data Index: 4811853 (Open Web Text)

Max Activating Token Index: 273

Text #18

Max Range: 3.1779. Min Range: -3.1779

Max Act: 2.9489. Min Act: -0.1700

Data Index: 5028842 (Open Web Text)

Max Activating Token Index: 588

Text #19

Max Range: 3.1779. Min Range: -3.1779

Max Act: 2.9637. Min Act: -0.1700

Data Index: 190423 (Open Web Text)

Max Activating Token Index: 184