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

Dataset: Open Web Text

Neuron 2271 in Layer 3

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: 4.2115. Min Range: -4.2115

Max Act: 4.2115. Min Act: -0.1700

Data Index: 7479982 (Open Web Text)

Max Activating Token Index: 254

Text #1

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.1437. Min Act: -0.1700

Data Index: 4610973 (Open Web Text)

Max Activating Token Index: 724

Text #2

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0842. Min Act: -0.1700

Data Index: 4728119 (Open Web Text)

Max Activating Token Index: 214

Text #3

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0554. Min Act: -0.1700

Data Index: 3918047 (Open Web Text)

Max Activating Token Index: 413

Text #4

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.1112. Min Act: -0.1700

Data Index: 7794579 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0712. Min Act: -0.1700

Data Index: 5936477 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0713. Min Act: -0.1700

Data Index: 3918046 (Open Web Text)

Max Activating Token Index: 939

Text #7

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0966. Min Act: -0.1700

Data Index: 3202112 (Open Web Text)

Max Activating Token Index: 34

Text #8

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.1047. Min Act: -0.1700

Data Index: 7362805 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0672. Min Act: -0.1700

Data Index: 7215463 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0689. Min Act: -0.1700

Data Index: 3870108 (Open Web Text)

Max Activating Token Index: 332

Text #11

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0382. Min Act: -0.1700

Data Index: 4947215 (Open Web Text)

Max Activating Token Index: 290

Text #12

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0884. Min Act: -0.1700

Data Index: 1637555 (Open Web Text)

Max Activating Token Index: 488

Text #13

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0387. Min Act: -0.1700

Data Index: 4537759 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0311. Min Act: -0.1700

Data Index: 4111047 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0728. Min Act: -0.1700

Data Index: 1911349 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0710. Min Act: -0.1700

Data Index: 2538378 (Open Web Text)

Max Activating Token Index: 706

Text #17

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0375. Min Act: -0.1700

Data Index: 1867242 (Open Web Text)

Max Activating Token Index: 988

Text #18

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0430. Min Act: -0.1700

Data Index: 5171903 (Open Web Text)

Max Activating Token Index: 700

Text #19

Max Range: 4.2115. Min Range: -4.2115

Max Act: 4.0182. Min Act: -0.1700

Data Index: 5581219 (Open Web Text)

Max Activating Token Index: 3