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

Dataset: Open Web Text

Neuron 364 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: 2.6895. Min Range: -2.6895

Max Act: 2.6895. Min Act: -0.1700

Data Index: 6631558 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6820. Min Act: -0.1700

Data Index: 2823705 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6450. Min Act: -0.1700

Data Index: 6229648 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6447. Min Act: -0.1700

Data Index: 2434984 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6488. Min Act: -0.1700

Data Index: 7000475 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6450. Min Act: -0.1700

Data Index: 7179740 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6419. Min Act: -0.1700

Data Index: 7808350 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6211. Min Act: -0.1700

Data Index: 5507212 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6300. Min Act: -0.1700

Data Index: 6019308 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6311. Min Act: -0.1700

Data Index: 6892000 (Open Web Text)

Max Activating Token Index: 30

Text #10

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6101. Min Act: -0.1700

Data Index: 3829841 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6038. Min Act: -0.1700

Data Index: 5089792 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6038. Min Act: -0.1700

Data Index: 3601768 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6038. Min Act: -0.1700

Data Index: 4161162 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6038. Min Act: -0.1700

Data Index: 3847949 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6181. Min Act: -0.1700

Data Index: 3110783 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6112. Min Act: -0.1700

Data Index: 3857025 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6038. Min Act: -0.1700

Data Index: 5161331 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6112. Min Act: -0.1700

Data Index: 4253554 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.6895. Min Range: -2.6895

Max Act: 2.6112. Min Act: -0.1700

Data Index: 5210513 (Open Web Text)

Max Activating Token Index: 2