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

Dataset: Open Web Text

Neuron 859 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: 3.0838. Min Range: -3.0838

Max Act: 3.0785. Min Act: -0.1700

Data Index: 6808755 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.0838. Min Range: -3.0838

Max Act: 3.0838. Min Act: -0.1700

Data Index: 7034561 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.0838. Min Range: -3.0838

Max Act: 3.0444. Min Act: -0.1700

Data Index: 1668472 (Open Web Text)

Max Activating Token Index: 514

Text #3

Max Range: 3.0838. Min Range: -3.0838

Max Act: 3.0274. Min Act: -0.1700

Data Index: 153143 (Open Web Text)

Max Activating Token Index: 688

Text #4

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9915. Min Act: -0.1700

Data Index: 3727953 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.0838. Min Range: -3.0838

Max Act: 3.0090. Min Act: -0.1700

Data Index: 5374384 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9955. Min Act: -0.1700

Data Index: 4835063 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9868. Min Act: -0.1700

Data Index: 2590634 (Open Web Text)

Max Activating Token Index: 22

Text #8

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9925. Min Act: -0.1700

Data Index: 1197324 (Open Web Text)

Max Activating Token Index: 752

Text #9

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9753. Min Act: -0.1700

Data Index: 2562748 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9736. Min Act: -0.1700

Data Index: 3157125 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9702. Min Act: -0.1700

Data Index: 6897330 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9565. Min Act: -0.1700

Data Index: 2919750 (Open Web Text)

Max Activating Token Index: 27

Text #13

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9703. Min Act: -0.1700

Data Index: 2149974 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9602. Min Act: -0.1700

Data Index: 2673042 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9681. Min Act: -0.1700

Data Index: 917753 (Open Web Text)

Max Activating Token Index: 655

Text #16

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9738. Min Act: -0.1700

Data Index: 3899725 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9548. Min Act: -0.1700

Data Index: 5118185 (Open Web Text)

Max Activating Token Index: 256

Text #18

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9484. Min Act: -0.1700

Data Index: 839272 (Open Web Text)

Max Activating Token Index: 591

Text #19

Max Range: 3.0838. Min Range: -3.0838

Max Act: 2.9005. Min Act: -0.1700

Data Index: 1187029 (Open Web Text)

Max Activating Token Index: 856