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

Dataset: Open Web Text

Neuron 1274 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: 2.3958. Min Range: -2.3958

Max Act: 2.3958. Min Act: -0.1700

Data Index: 5824930 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.3578. Min Act: -0.1700

Data Index: 2137673 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.3137. Min Act: -0.1700

Data Index: 4893736 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.3183. Min Act: -0.1700

Data Index: 6325185 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.3131. Min Act: -0.1700

Data Index: 2068501 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.2593. Min Act: -0.1700

Data Index: 4383819 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.2524. Min Act: -0.1700

Data Index: 7233358 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.2406. Min Act: -0.1700

Data Index: 743668 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.2200. Min Act: -0.1700

Data Index: 488390 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.2006. Min Act: -0.1700

Data Index: 4892579 (Open Web Text)

Max Activating Token Index: 1

Text #10

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.2006. Min Act: -0.1700

Data Index: 2705916 (Open Web Text)

Max Activating Token Index: 1

Text #11

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.1896. Min Act: -0.1700

Data Index: 5047855 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.1851. Min Act: -0.1700

Data Index: 6470896 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.1514. Min Act: -0.1700

Data Index: 3671196 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.1572. Min Act: -0.1700

Data Index: 1673084 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.1538. Min Act: -0.1700

Data Index: 1252442 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.1387. Min Act: -0.1700

Data Index: 1759780 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.1392. Min Act: -0.1700

Data Index: 2555679 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.1272. Min Act: -0.1700

Data Index: 4153629 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 2.3958. Min Range: -2.3958

Max Act: 2.1272. Min Act: -0.1700

Data Index: 2089421 (Open Web Text)

Max Activating Token Index: 1