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

Dataset: Open Web Text

Neuron 2091 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: 4.0211. Min Range: -4.0211

Max Act: 4.0211. Min Act: -0.1700

Data Index: 2443662 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.0211. Min Range: -4.0211

Max Act: 4.0211. Min Act: -0.1700

Data Index: 1405805 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.0211. Min Range: -4.0211

Max Act: 4.0211. Min Act: -0.1700

Data Index: 831835 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.0211. Min Range: -4.0211

Max Act: 4.0211. Min Act: -0.1700

Data Index: 4949747 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.9481. Min Act: -0.1700

Data Index: 4176394 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.9517. Min Act: -0.1700

Data Index: 7418836 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.9278. Min Act: -0.1700

Data Index: 13826 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.9056. Min Act: -0.1700

Data Index: 7849550 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.9018. Min Act: -0.1700

Data Index: 2190954 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8999. Min Act: -0.1700

Data Index: 4026976 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8954. Min Act: -0.1700

Data Index: 715940 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8833. Min Act: -0.1700

Data Index: 5058331 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8969. Min Act: -0.1700

Data Index: 1126575 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8841. Min Act: -0.1700

Data Index: 6613746 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8627. Min Act: -0.1700

Data Index: 2912306 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8597. Min Act: -0.1700

Data Index: 925213 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8531. Min Act: -0.1700

Data Index: 4467838 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8720. Min Act: -0.1700

Data Index: 1576355 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8645. Min Act: -0.1700

Data Index: 895039 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.0211. Min Range: -4.0211

Max Act: 3.8554. Min Act: -0.1700

Data Index: 849488 (Open Web Text)

Max Activating Token Index: 4