Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 1959 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')

Text #0

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.8320. Min Act: -0.1700

Data Index: 981392 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.8002. Min Act: -0.1700

Data Index: 2103787 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6884. Min Act: -0.1700

Data Index: 3948867 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.7204. Min Act: -0.1700

Data Index: 7902235 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6564. Min Act: -0.1700

Data Index: 3481821 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6403. Min Act: -0.1700

Data Index: 4209055 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6564. Min Act: -0.1700

Data Index: 6244962 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6403. Min Act: -0.1700

Data Index: 2542704 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6403. Min Act: -0.1700

Data Index: 8395357 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6243. Min Act: -0.1700

Data Index: 2064925 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6243. Min Act: -0.1700

Data Index: 6323692 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6243. Min Act: -0.1700

Data Index: 7254597 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6082. Min Act: -0.1700

Data Index: 8556394 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6243. Min Act: -0.1700

Data Index: 4412432 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6243. Min Act: -0.1700

Data Index: 3122279 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6082. Min Act: -0.1700

Data Index: 2692023 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6082. Min Act: -0.1700

Data Index: 1861950 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5760. Min Act: -0.1700

Data Index: 6290401 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5921. Min Act: -0.1700

Data Index: 7461780 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5921. Min Act: -0.1700

Data Index: 411119 (Open Web Text)

Max Activating Token Index: 7