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

Dataset: Open Web Text

Neuron 3054 in Layer 0

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: 7.3231. Min Range: -7.3231

Max Act: 7.3231. Min Act: -0.1700

Data Index: 1063562 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.2908. Min Act: -0.1700

Data Index: 7715021 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.2353. Min Act: -0.1700

Data Index: 1796704 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.2858. Min Act: -0.1700

Data Index: 4856688 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.2439. Min Act: -0.1700

Data Index: 5325497 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.1795. Min Act: -0.1700

Data Index: 6863484 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.1938. Min Act: -0.1700

Data Index: 176895 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.1894. Min Act: -0.1700

Data Index: 1172627 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.2068. Min Act: -0.1689

Data Index: 8401190 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.1894. Min Act: -0.1700

Data Index: 8019284 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.1818. Min Act: -0.1700

Data Index: 7865525 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.1673. Min Act: -0.1698

Data Index: 21696 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.2068. Min Act: -0.1700

Data Index: 5498929 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.1901. Min Act: -0.1700

Data Index: 784327 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.1871. Min Act: -0.1700

Data Index: 778205 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.1990. Min Act: -0.1700

Data Index: 5245205 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.1694. Min Act: -0.1700

Data Index: 4935385 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.1990. Min Act: -0.1700

Data Index: 4783954 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.1326. Min Act: -0.1700

Data Index: 508118 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 7.3231. Min Range: -7.3231

Max Act: 7.0967. Min Act: -0.1696

Data Index: 1233349 (Open Web Text)

Max Activating Token Index: 4