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

Dataset: Open Web Text

Neuron 464 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: 1.7831. Min Range: -1.7831

Max Act: 1.7831. Min Act: -0.1700

Data Index: 1051750 (Open Web Text)

Max Activating Token Index: 403

Text #1

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7810. Min Act: -0.1700

Data Index: 6811348 (Open Web Text)

Max Activating Token Index: 378

Text #2

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7494. Min Act: -0.1700

Data Index: 1522538 (Open Web Text)

Max Activating Token Index: 465

Text #3

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7558. Min Act: -0.1700

Data Index: 5686810 (Open Web Text)

Max Activating Token Index: 760

Text #4

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7640. Min Act: -0.1700

Data Index: 1895957 (Open Web Text)

Max Activating Token Index: 737

Text #5

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7619. Min Act: -0.1700

Data Index: 556368 (Open Web Text)

Max Activating Token Index: 750

Text #6

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7532. Min Act: -0.1700

Data Index: 3954512 (Open Web Text)

Max Activating Token Index: 893

Text #7

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7568. Min Act: -0.1700

Data Index: 4895151 (Open Web Text)

Max Activating Token Index: 278

Text #8

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7439. Min Act: -0.1700

Data Index: 3511491 (Open Web Text)

Max Activating Token Index: 617

Text #9

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7276. Min Act: -0.1700

Data Index: 66325 (Open Web Text)

Max Activating Token Index: 952

Text #10

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7245. Min Act: -0.1700

Data Index: 1807618 (Open Web Text)

Max Activating Token Index: 994

Text #11

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7175. Min Act: -0.1700

Data Index: 3124535 (Open Web Text)

Max Activating Token Index: 502

Text #12

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7083. Min Act: -0.1700

Data Index: 2570727 (Open Web Text)

Max Activating Token Index: 254

Text #13

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7144. Min Act: -0.1700

Data Index: 439636 (Open Web Text)

Max Activating Token Index: 654

Text #14

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7187. Min Act: -0.1700

Data Index: 3631079 (Open Web Text)

Max Activating Token Index: 723

Text #15

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7188. Min Act: -0.1700

Data Index: 7467555 (Open Web Text)

Max Activating Token Index: 256

Text #16

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7211. Min Act: -0.1700

Data Index: 2455346 (Open Web Text)

Max Activating Token Index: 543

Text #17

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7083. Min Act: -0.1700

Data Index: 8786330 (Open Web Text)

Max Activating Token Index: 974

Text #18

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.7071. Min Act: -0.1700

Data Index: 2198163 (Open Web Text)

Max Activating Token Index: 872

Text #19

Max Range: 1.7831. Min Range: -1.7831

Max Act: 1.6996. Min Act: -0.1700

Data Index: 6742251 (Open Web Text)

Max Activating Token Index: 392