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

Dataset: Open Web Text

Neuron 1622 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: 3.3711. Min Range: -3.3711

Max Act: 3.3711. Min Act: -0.1700

Data Index: 2722393 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2339. Min Act: -0.1700

Data Index: 3801146 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2220. Min Act: -0.1700

Data Index: 2557589 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2162. Min Act: -0.1700

Data Index: 753495 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.1980. Min Act: -0.1700

Data Index: 1984964 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2075. Min Act: -0.1700

Data Index: 379051 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.1993. Min Act: -0.1700

Data Index: 777436 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2044. Min Act: -0.1700

Data Index: 7648409 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.2004. Min Act: -0.1700

Data Index: 1439255 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.1827. Min Act: -0.1700

Data Index: 4378890 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.1984. Min Act: -0.1700

Data Index: 1481117 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.1850. Min Act: -0.1700

Data Index: 4353663 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.1984. Min Act: -0.1700

Data Index: 6054892 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.1938. Min Act: -0.1700

Data Index: 5855098 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.1984. Min Act: -0.1700

Data Index: 5742792 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.1984. Min Act: -0.1700

Data Index: 7713694 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.1984. Min Act: -0.1700

Data Index: 379050 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.1940. Min Act: -0.1700

Data Index: 3387539 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.1751. Min Act: -0.1700

Data Index: 93394 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.3711. Min Range: -3.3711

Max Act: 3.1598. Min Act: -0.1700

Data Index: 3309065 (Open Web Text)

Max Activating Token Index: 20