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

Dataset: Open Web Text

Neuron 55 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: 3.9954. Min Range: -3.9954

Max Act: 3.9954. Min Act: -0.1700

Data Index: 741251 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.9865. Min Act: -0.1700

Data Index: 805090 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.9662. Min Act: -0.1700

Data Index: 7489113 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.9581. Min Act: -0.1700

Data Index: 5476178 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.9335. Min Act: -0.1700

Data Index: 8264538 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.9426. Min Act: -0.1700

Data Index: 6194033 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.8997. Min Act: -0.1700

Data Index: 1909037 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.9227. Min Act: -0.1700

Data Index: 574954 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.8793. Min Act: -0.1700

Data Index: 4627912 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.8701. Min Act: -0.1700

Data Index: 7066906 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.8653. Min Act: -0.1700

Data Index: 6840834 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.8723. Min Act: -0.1700

Data Index: 4859995 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.8701. Min Act: -0.1700

Data Index: 6443387 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.8645. Min Act: -0.1700

Data Index: 4634135 (Open Web Text)

Max Activating Token Index: 37

Text #14

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.8847. Min Act: -0.1700

Data Index: 6176169 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.8802. Min Act: -0.1700

Data Index: 4503310 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.8847. Min Act: -0.1700

Data Index: 5838298 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.8582. Min Act: -0.1700

Data Index: 1228591 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.8782. Min Act: -0.1700

Data Index: 5160708 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 3.9954. Min Range: -3.9954

Max Act: 3.8936. Min Act: -0.1700

Data Index: 4497049 (Open Web Text)

Max Activating Token Index: 5