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

Dataset: Open Web Text

Neuron 2175 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: 4.2654. Min Range: -4.2654

Max Act: 4.2654. Min Act: -0.1700

Data Index: 1502789 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.1919. Min Act: -0.1700

Data Index: 6787614 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.1483. Min Act: -0.1700

Data Index: 8127937 (Open Web Text)

Max Activating Token Index: 971

Text #3

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.1571. Min Act: -0.1700

Data Index: 887116 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.1381. Min Act: -0.1700

Data Index: 4760277 (Open Web Text)

Max Activating Token Index: 537

Text #5

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.1623. Min Act: -0.1700

Data Index: 1221869 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.1573. Min Act: -0.1700

Data Index: 952572 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.1176. Min Act: -0.1700

Data Index: 1070874 (Open Web Text)

Max Activating Token Index: 222

Text #8

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.1184. Min Act: -0.1700

Data Index: 5045120 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.1153. Min Act: -0.1700

Data Index: 5076165 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.1274. Min Act: -0.1700

Data Index: 1554225 (Open Web Text)

Max Activating Token Index: 45

Text #11

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.0921. Min Act: -0.1700

Data Index: 7251964 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.0965. Min Act: -0.1700

Data Index: 3456774 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.0954. Min Act: -0.1700

Data Index: 8014002 (Open Web Text)

Max Activating Token Index: 953

Text #14

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.0945. Min Act: -0.1700

Data Index: 7665349 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.0981. Min Act: -0.1700

Data Index: 7550202 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.0879. Min Act: -0.1700

Data Index: 5371457 (Open Web Text)

Max Activating Token Index: 794

Text #17

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.0979. Min Act: -0.1700

Data Index: 5043398 (Open Web Text)

Max Activating Token Index: 60

Text #18

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.1126. Min Act: -0.1700

Data Index: 4345328 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.2654. Min Range: -4.2654

Max Act: 4.0709. Min Act: -0.1700

Data Index: 3584872 (Open Web Text)

Max Activating Token Index: 11