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

Dataset: Open Web Text

Neuron 2905 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: 5.2887. Min Range: -5.2887

Max Act: 5.2842. Min Act: -0.1700

Data Index: 1289649 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 5.2887. Min Range: -5.2887

Max Act: 5.2887. Min Act: -0.1700

Data Index: 3893455 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 5.2887. Min Range: -5.2887

Max Act: 5.1901. Min Act: -0.1700

Data Index: 2209341 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 5.2887. Min Range: -5.2887

Max Act: 5.1662. Min Act: -0.1700

Data Index: 3081046 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 5.2887. Min Range: -5.2887

Max Act: 5.1266. Min Act: -0.1700

Data Index: 4942792 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.2887. Min Range: -5.2887

Max Act: 5.0494. Min Act: -0.1700

Data Index: 7707994 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.2887. Min Range: -5.2887

Max Act: 5.0511. Min Act: -0.1700

Data Index: 3365719 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.2887. Min Range: -5.2887

Max Act: 5.0610. Min Act: -0.1700

Data Index: 70422 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 5.2887. Min Range: -5.2887

Max Act: 5.0480. Min Act: -0.1700

Data Index: 957363 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 5.2887. Min Range: -5.2887

Max Act: 5.0230. Min Act: -0.1700

Data Index: 2302845 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.2887. Min Range: -5.2887

Max Act: 5.0299. Min Act: -0.1700

Data Index: 8184131 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.2887. Min Range: -5.2887

Max Act: 4.9927. Min Act: -0.1700

Data Index: 8316606 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 5.2887. Min Range: -5.2887

Max Act: 4.9804. Min Act: -0.1700

Data Index: 3027677 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.2887. Min Range: -5.2887

Max Act: 4.9681. Min Act: -0.1700

Data Index: 2092009 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.2887. Min Range: -5.2887

Max Act: 4.9586. Min Act: -0.1700

Data Index: 2081435 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.2887. Min Range: -5.2887

Max Act: 4.9605. Min Act: -0.1700

Data Index: 5665491 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 5.2887. Min Range: -5.2887

Max Act: 4.9588. Min Act: -0.1700

Data Index: 5740636 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 5.2887. Min Range: -5.2887

Max Act: 4.9586. Min Act: -0.1700

Data Index: 894743 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.2887. Min Range: -5.2887

Max Act: 4.9574. Min Act: -0.1700

Data Index: 540404 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 5.2887. Min Range: -5.2887

Max Act: 4.9588. Min Act: -0.1700

Data Index: 96768 (Open Web Text)

Max Activating Token Index: 2