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

Dataset: Open Web Text

Neuron 2515 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: 3.0032. Min Range: -3.0032

Max Act: 3.0032. Min Act: -0.1700

Data Index: 2691492 (Open Web Text)

Max Activating Token Index: 356

Text #1

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9902. Min Act: -0.1700

Data Index: 6789200 (Open Web Text)

Max Activating Token Index: 276

Text #2

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9670. Min Act: -0.1700

Data Index: 3797015 (Open Web Text)

Max Activating Token Index: 512

Text #3

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9732. Min Act: -0.1700

Data Index: 7199724 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9437. Min Act: -0.1700

Data Index: 2917871 (Open Web Text)

Max Activating Token Index: 598

Text #5

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9401. Min Act: -0.1700

Data Index: 4578826 (Open Web Text)

Max Activating Token Index: 333

Text #6

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9412. Min Act: -0.1700

Data Index: 5329732 (Open Web Text)

Max Activating Token Index: 540

Text #7

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9441. Min Act: -0.1700

Data Index: 326456 (Open Web Text)

Max Activating Token Index: 435

Text #8

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9403. Min Act: -0.1700

Data Index: 8591982 (Open Web Text)

Max Activating Token Index: 871

Text #9

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9476. Min Act: -0.1700

Data Index: 4645595 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9163. Min Act: -0.1700

Data Index: 3174055 (Open Web Text)

Max Activating Token Index: 313

Text #11

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9498. Min Act: -0.1700

Data Index: 4937302 (Open Web Text)

Max Activating Token Index: 443

Text #12

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9162. Min Act: -0.1700

Data Index: 5656973 (Open Web Text)

Max Activating Token Index: 41

Text #13

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.8894. Min Act: -0.1700

Data Index: 6590771 (Open Web Text)

Max Activating Token Index: 334

Text #14

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.8901. Min Act: -0.1700

Data Index: 296773 (Open Web Text)

Max Activating Token Index: 83

Text #15

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9142. Min Act: -0.1700

Data Index: 3850034 (Open Web Text)

Max Activating Token Index: 406

Text #16

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.8958. Min Act: -0.1700

Data Index: 2854834 (Open Web Text)

Max Activating Token Index: 990

Text #17

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.8902. Min Act: -0.1700

Data Index: 6942740 (Open Web Text)

Max Activating Token Index: 202

Text #18

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.8955. Min Act: -0.1700

Data Index: 2406366 (Open Web Text)

Max Activating Token Index: 459

Text #19

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.9002. Min Act: -0.1700

Data Index: 1376348 (Open Web Text)

Max Activating Token Index: 222