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

Dataset: Open Web Text

Neuron 1455 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: 4.3001. Min Range: -4.3001

Max Act: 4.3001. Min Act: -0.1700

Data Index: 1553256 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 4.3001. Min Range: -4.3001

Max Act: 4.1445. Min Act: -0.1700

Data Index: 759379 (Open Web Text)

Max Activating Token Index: 307

Text #2

Max Range: 4.3001. Min Range: -4.3001

Max Act: 4.0578. Min Act: -0.1700

Data Index: 8758713 (Open Web Text)

Max Activating Token Index: 214

Text #3

Max Range: 4.3001. Min Range: -4.3001

Max Act: 4.0935. Min Act: -0.1700

Data Index: 1809903 (Open Web Text)

Max Activating Token Index: 38

Text #4

Max Range: 4.3001. Min Range: -4.3001

Max Act: 4.0911. Min Act: -0.1700

Data Index: 6873906 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.3001. Min Range: -4.3001

Max Act: 4.0197. Min Act: -0.1700

Data Index: 7424821 (Open Web Text)

Max Activating Token Index: 1011

Text #6

Max Range: 4.3001. Min Range: -4.3001

Max Act: 4.0195. Min Act: -0.1700

Data Index: 4516680 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.3001. Min Range: -4.3001

Max Act: 4.0314. Min Act: -0.1700

Data Index: 4828856 (Open Web Text)

Max Activating Token Index: 419

Text #8

Max Range: 4.3001. Min Range: -4.3001

Max Act: 4.0082. Min Act: -0.1700

Data Index: 5034404 (Open Web Text)

Max Activating Token Index: 466

Text #9

Max Range: 4.3001. Min Range: -4.3001

Max Act: 4.0279. Min Act: -0.1700

Data Index: 5409432 (Open Web Text)

Max Activating Token Index: 945

Text #10

Max Range: 4.3001. Min Range: -4.3001

Max Act: 3.9949. Min Act: -0.1700

Data Index: 1526808 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 4.3001. Min Range: -4.3001

Max Act: 3.9953. Min Act: -0.1700

Data Index: 1096062 (Open Web Text)

Max Activating Token Index: 988

Text #12

Max Range: 4.3001. Min Range: -4.3001

Max Act: 4.0305. Min Act: -0.1700

Data Index: 5344526 (Open Web Text)

Max Activating Token Index: 138

Text #13

Max Range: 4.3001. Min Range: -4.3001

Max Act: 3.9982. Min Act: -0.1700

Data Index: 7361455 (Open Web Text)

Max Activating Token Index: 552

Text #14

Max Range: 4.3001. Min Range: -4.3001

Max Act: 3.9537. Min Act: -0.1700

Data Index: 6029480 (Open Web Text)

Max Activating Token Index: 293

Text #15

Max Range: 4.3001. Min Range: -4.3001

Max Act: 3.9454. Min Act: -0.1700

Data Index: 2921619 (Open Web Text)

Max Activating Token Index: 197

Text #16

Max Range: 4.3001. Min Range: -4.3001

Max Act: 3.9946. Min Act: -0.1700

Data Index: 4856910 (Open Web Text)

Max Activating Token Index: 280

Text #17

Max Range: 4.3001. Min Range: -4.3001

Max Act: 4.0178. Min Act: -0.1700

Data Index: 579038 (Open Web Text)

Max Activating Token Index: 540

Text #18

Max Range: 4.3001. Min Range: -4.3001

Max Act: 3.9262. Min Act: -0.1700

Data Index: 979806 (Open Web Text)

Max Activating Token Index: 999

Text #19

Max Range: 4.3001. Min Range: -4.3001

Max Act: 3.9709. Min Act: -0.1700

Data Index: 4038355 (Open Web Text)

Max Activating Token Index: 287