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

Dataset: Open Web Text

Neuron 2719 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: 2.9799. Min Range: -2.9799

Max Act: 2.9799. Min Act: -0.1700

Data Index: 8590865 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.9065. Min Act: -0.1700

Data Index: 1324673 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.8540. Min Act: -0.1700

Data Index: 1951969 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.8204. Min Act: -0.1700

Data Index: 2023354 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.7974. Min Act: -0.1700

Data Index: 2566385 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.8004. Min Act: -0.1700

Data Index: 4873788 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.7794. Min Act: -0.1700

Data Index: 6821360 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.7580. Min Act: -0.1700

Data Index: 1261237 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.7538. Min Act: -0.1700

Data Index: 742597 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.7393. Min Act: -0.1700

Data Index: 2137585 (Open Web Text)

Max Activating Token Index: 85

Text #10

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.7415. Min Act: -0.1700

Data Index: 2495435 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.7227. Min Act: -0.1700

Data Index: 3730355 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.7320. Min Act: -0.1700

Data Index: 7863328 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.7280. Min Act: -0.1700

Data Index: 1513623 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.7023. Min Act: -0.1700

Data Index: 5426302 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.7046. Min Act: -0.1700

Data Index: 5654095 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.6999. Min Act: -0.1700

Data Index: 5873087 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.6995. Min Act: -0.1700

Data Index: 3582535 (Open Web Text)

Max Activating Token Index: 36

Text #18

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.7118. Min Act: -0.1700

Data Index: 1844954 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.7022. Min Act: -0.1700

Data Index: 7392996 (Open Web Text)

Max Activating Token Index: 4