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

Dataset: Open Web Text

Neuron 2143 in Layer 1

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: 3.0396. Min Range: -3.0396

Max Act: 3.0396. Min Act: -0.1700

Data Index: 1767823 (Open Web Text)

Max Activating Token Index: 269

Text #1

Max Range: 3.0396. Min Range: -3.0396

Max Act: 3.0178. Min Act: -0.1700

Data Index: 4265933 (Open Web Text)

Max Activating Token Index: 127

Text #2

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.9909. Min Act: -0.1700

Data Index: 1442117 (Open Web Text)

Max Activating Token Index: 217

Text #3

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.9927. Min Act: -0.1700

Data Index: 2915285 (Open Web Text)

Max Activating Token Index: 206

Text #4

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.9875. Min Act: -0.1700

Data Index: 7502990 (Open Web Text)

Max Activating Token Index: 129

Text #5

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.9985. Min Act: -0.1700

Data Index: 1565480 (Open Web Text)

Max Activating Token Index: 824

Text #6

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.9715. Min Act: -0.1700

Data Index: 7060918 (Open Web Text)

Max Activating Token Index: 606

Text #7

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.9758. Min Act: -0.1700

Data Index: 7998597 (Open Web Text)

Max Activating Token Index: 510

Text #8

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.9412. Min Act: -0.1700

Data Index: 7144047 (Open Web Text)

Max Activating Token Index: 143

Text #9

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.9309. Min Act: -0.1700

Data Index: 1827378 (Open Web Text)

Max Activating Token Index: 87

Text #10

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.9315. Min Act: -0.1700

Data Index: 5513470 (Open Web Text)

Max Activating Token Index: 144

Text #11

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.9248. Min Act: -0.1700

Data Index: 4598681 (Open Web Text)

Max Activating Token Index: 177

Text #12

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.9147. Min Act: -0.1700

Data Index: 2757558 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.9122. Min Act: -0.1700

Data Index: 2274070 (Open Web Text)

Max Activating Token Index: 143

Text #14

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.8976. Min Act: -0.1700

Data Index: 4296315 (Open Web Text)

Max Activating Token Index: 86

Text #15

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.8947. Min Act: -0.1700

Data Index: 7878630 (Open Web Text)

Max Activating Token Index: 494

Text #16

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.8875. Min Act: -0.1700

Data Index: 7013232 (Open Web Text)

Max Activating Token Index: 561

Text #17

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.8855. Min Act: -0.1700

Data Index: 4978455 (Open Web Text)

Max Activating Token Index: 210

Text #18

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.9012. Min Act: -0.1700

Data Index: 6864616 (Open Web Text)

Max Activating Token Index: 535

Text #19

Max Range: 3.0396. Min Range: -3.0396

Max Act: 2.8930. Min Act: -0.1700

Data Index: 6531288 (Open Web Text)

Max Activating Token Index: 613