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

Dataset: Open Web Text

Neuron 1956 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: 3.7251. Min Range: -3.7251

Max Act: 3.7251. Min Act: -0.1700

Data Index: 464419 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6851. Min Act: -0.1700

Data Index: 8436980 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6890. Min Act: -0.1700

Data Index: 7902422 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6770. Min Act: -0.1700

Data Index: 2189890 (Open Web Text)

Max Activating Token Index: 25

Text #4

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6651. Min Act: -0.1700

Data Index: 6590808 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6512. Min Act: -0.1700

Data Index: 7439457 (Open Web Text)

Max Activating Token Index: 35

Text #6

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6588. Min Act: -0.1700

Data Index: 7755878 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6362. Min Act: -0.1700

Data Index: 1065913 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6223. Min Act: -0.1700

Data Index: 8314685 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6442. Min Act: -0.1700

Data Index: 5584468 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6440. Min Act: -0.1700

Data Index: 2208895 (Open Web Text)

Max Activating Token Index: 27

Text #11

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6101. Min Act: -0.1700

Data Index: 929545 (Open Web Text)

Max Activating Token Index: 16

Text #12

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6359. Min Act: -0.1700

Data Index: 7099055 (Open Web Text)

Max Activating Token Index: 22

Text #13

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6303. Min Act: -0.1700

Data Index: 7018142 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6099. Min Act: -0.1700

Data Index: 4598193 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6342. Min Act: -0.1700

Data Index: 6695340 (Open Web Text)

Max Activating Token Index: 676

Text #16

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6178. Min Act: -0.1700

Data Index: 6675876 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6266. Min Act: -0.1700

Data Index: 1822076 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.6200. Min Act: -0.1700

Data Index: 2559791 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 3.7251. Min Range: -3.7251

Max Act: 3.5941. Min Act: -0.1700

Data Index: 409792 (Open Web Text)

Max Activating Token Index: 13