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

Dataset: Open Web Text

Neuron 768 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: 1.7315. Min Range: -1.7315

Max Act: 1.7315. Min Act: -0.1700

Data Index: 3368796 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.7081. Min Act: -0.1700

Data Index: 6477851 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6861. Min Act: -0.1700

Data Index: 7141569 (Open Web Text)

Max Activating Token Index: 78

Text #3

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6798. Min Act: -0.1700

Data Index: 6709044 (Open Web Text)

Max Activating Token Index: 650

Text #4

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6938. Min Act: -0.1700

Data Index: 1913917 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6744. Min Act: -0.1700

Data Index: 5298220 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6663. Min Act: -0.1700

Data Index: 5820420 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6624. Min Act: -0.1700

Data Index: 5812447 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6712. Min Act: -0.1700

Data Index: 3297068 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6662. Min Act: -0.1700

Data Index: 2044646 (Open Web Text)

Max Activating Token Index: 28

Text #10

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6536. Min Act: -0.1700

Data Index: 398473 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6537. Min Act: -0.1700

Data Index: 1451185 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6582. Min Act: -0.1700

Data Index: 1343763 (Open Web Text)

Max Activating Token Index: 280

Text #13

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6484. Min Act: -0.1700

Data Index: 5114455 (Open Web Text)

Max Activating Token Index: 17

Text #14

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6416. Min Act: -0.1700

Data Index: 1095287 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6493. Min Act: -0.1700

Data Index: 8614727 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6520. Min Act: -0.1700

Data Index: 7185012 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6426. Min Act: -0.1700

Data Index: 7993836 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6280. Min Act: -0.1700

Data Index: 5741021 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6311. Min Act: -0.1700

Data Index: 2735734 (Open Web Text)

Max Activating Token Index: 5