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

Dataset: Open Web Text

Neuron 551 in Layer 1

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: 1.7748. Min Range: -1.7748

Max Act: 1.7748. Min Act: -0.1700

Data Index: 837587 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7468. Min Act: -0.1699

Data Index: 4627447 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7197. Min Act: -0.1684

Data Index: 630588 (Open Web Text)

Max Activating Token Index: 351

Text #3

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7279. Min Act: -0.1700

Data Index: 8477730 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7191. Min Act: -0.1700

Data Index: 2105962 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7028. Min Act: -0.1700

Data Index: 868891 (Open Web Text)

Max Activating Token Index: 25

Text #6

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7025. Min Act: -0.1700

Data Index: 6598936 (Open Web Text)

Max Activating Token Index: 42

Text #7

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7019. Min Act: -0.1700

Data Index: 2341898 (Open Web Text)

Max Activating Token Index: 63

Text #8

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7049. Min Act: -0.1700

Data Index: 2095574 (Open Web Text)

Max Activating Token Index: 170

Text #9

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.7113. Min Act: -0.1696

Data Index: 3719245 (Open Web Text)

Max Activating Token Index: 687

Text #10

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.6922. Min Act: -0.1700

Data Index: 3628113 (Open Web Text)

Max Activating Token Index: 561

Text #11

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.6940. Min Act: -0.1700

Data Index: 579014 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.6855. Min Act: -0.1699

Data Index: 65464 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.6808. Min Act: -0.1700

Data Index: 1386566 (Open Web Text)

Max Activating Token Index: 309

Text #14

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.6842. Min Act: -0.1700

Data Index: 2758178 (Open Web Text)

Max Activating Token Index: 29

Text #15

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.6795. Min Act: -0.1700

Data Index: 8445178 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.6635. Min Act: -0.1700

Data Index: 2422169 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.6705. Min Act: -0.1700

Data Index: 484654 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.6688. Min Act: -0.1700

Data Index: 8564213 (Open Web Text)

Max Activating Token Index: 69

Text #19

Max Range: 1.7748. Min Range: -1.7748

Max Act: 1.6666. Min Act: -0.1700

Data Index: 360348 (Open Web Text)

Max Activating Token Index: 135