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

Dataset: Open Web Text

Neuron 1656 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: 3.1006. Min Range: -3.1006

Max Act: 3.1006. Min Act: -0.1700

Data Index: 4310746 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0663. Min Act: -0.1700

Data Index: 3341574 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0517. Min Act: -0.1700

Data Index: 3942681 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0400. Min Act: -0.1700

Data Index: 8649213 (Open Web Text)

Max Activating Token Index: 29

Text #4

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0202. Min Act: -0.1700

Data Index: 4045640 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0172. Min Act: -0.1700

Data Index: 3972121 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0137. Min Act: -0.1700

Data Index: 6814002 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0160. Min Act: -0.1700

Data Index: 5625762 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0030. Min Act: -0.1700

Data Index: 8157070 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9889. Min Act: -0.1700

Data Index: 6710242 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9669. Min Act: -0.1700

Data Index: 4726987 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9765. Min Act: -0.1700

Data Index: 8266680 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9692. Min Act: -0.1700

Data Index: 8537169 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9748. Min Act: -0.1700

Data Index: 1487380 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9749. Min Act: -0.1700

Data Index: 2400674 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9694. Min Act: -0.1700

Data Index: 2723278 (Open Web Text)

Max Activating Token Index: 329

Text #16

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9587. Min Act: -0.1700

Data Index: 3607679 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9564. Min Act: -0.1700

Data Index: 4813355 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9499. Min Act: -0.1700

Data Index: 7682927 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9520. Min Act: -0.1700

Data Index: 2316849 (Open Web Text)

Max Activating Token Index: 856