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

Dataset: Open Web Text

Neuron 1007 in Layer 5

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: 3.1913. Min Range: -3.1913

Max Act: 3.1913. Min Act: -0.1700

Data Index: 1896421 (Open Web Text)

Max Activating Token Index: 597

Text #1

Max Range: 3.1913. Min Range: -3.1913

Max Act: 3.1106. Min Act: -0.1700

Data Index: 5647266 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 3.1913. Min Range: -3.1913

Max Act: 3.0762. Min Act: -0.1700

Data Index: 2041102 (Open Web Text)

Max Activating Token Index: 1006

Text #3

Max Range: 3.1913. Min Range: -3.1913

Max Act: 3.0675. Min Act: -0.1700

Data Index: 8552029 (Open Web Text)

Max Activating Token Index: 802

Text #4

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.9499. Min Act: -0.1700

Data Index: 4624624 (Open Web Text)

Max Activating Token Index: 932

Text #5

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.9610. Min Act: -0.1700

Data Index: 7198985 (Open Web Text)

Max Activating Token Index: 269

Text #6

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.9520. Min Act: -0.1700

Data Index: 827686 (Open Web Text)

Max Activating Token Index: 101

Text #7

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.9197. Min Act: -0.1700

Data Index: 1286887 (Open Web Text)

Max Activating Token Index: 553

Text #8

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.9277. Min Act: -0.1700

Data Index: 7134208 (Open Web Text)

Max Activating Token Index: 82

Text #9

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.9039. Min Act: -0.1700

Data Index: 6890616 (Open Web Text)

Max Activating Token Index: 639

Text #10

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.9085. Min Act: -0.1700

Data Index: 3400075 (Open Web Text)

Max Activating Token Index: 344

Text #11

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.9061. Min Act: -0.1700

Data Index: 8425888 (Open Web Text)

Max Activating Token Index: 451

Text #12

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.8817. Min Act: -0.1700

Data Index: 4799839 (Open Web Text)

Max Activating Token Index: 268

Text #13

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.8867. Min Act: -0.1700

Data Index: 6522817 (Open Web Text)

Max Activating Token Index: 265

Text #14

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.8592. Min Act: -0.1700

Data Index: 8198058 (Open Web Text)

Max Activating Token Index: 124

Text #15

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.8775. Min Act: -0.1700

Data Index: 6464887 (Open Web Text)

Max Activating Token Index: 435

Text #16

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.8771. Min Act: -0.1700

Data Index: 463597 (Open Web Text)

Max Activating Token Index: 972

Text #17

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.8447. Min Act: -0.1700

Data Index: 4409916 (Open Web Text)

Max Activating Token Index: 537

Text #18

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.8469. Min Act: -0.1700

Data Index: 2430938 (Open Web Text)

Max Activating Token Index: 67

Text #19

Max Range: 3.1913. Min Range: -3.1913

Max Act: 2.8546. Min Act: -0.1700

Data Index: 3564833 (Open Web Text)

Max Activating Token Index: 414