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

Dataset: Open Web Text

Neuron 329 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: 4.8624. Min Range: -4.8624

Max Act: 4.8624. Min Act: -0.1700

Data Index: 7614340 (Open Web Text)

Max Activating Token Index: 487

Text #1

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.7158. Min Act: -0.1700

Data Index: 7606555 (Open Web Text)

Max Activating Token Index: 736

Text #2

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.6739. Min Act: -0.1700

Data Index: 5758831 (Open Web Text)

Max Activating Token Index: 465

Text #3

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.6466. Min Act: -0.1700

Data Index: 4352176 (Open Web Text)

Max Activating Token Index: 729

Text #4

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5987. Min Act: -0.1700

Data Index: 1619195 (Open Web Text)

Max Activating Token Index: 690

Text #5

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5814. Min Act: -0.1700

Data Index: 4261331 (Open Web Text)

Max Activating Token Index: 133

Text #6

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5867. Min Act: -0.1700

Data Index: 6438299 (Open Web Text)

Max Activating Token Index: 677

Text #7

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5621. Min Act: -0.1700

Data Index: 5580361 (Open Web Text)

Max Activating Token Index: 1009

Text #8

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.6026. Min Act: -0.1700

Data Index: 7403398 (Open Web Text)

Max Activating Token Index: 671

Text #9

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5904. Min Act: -0.1700

Data Index: 7522102 (Open Web Text)

Max Activating Token Index: 678

Text #10

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5386. Min Act: -0.1700

Data Index: 8202413 (Open Web Text)

Max Activating Token Index: 812

Text #11

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5708. Min Act: -0.1700

Data Index: 6289836 (Open Web Text)

Max Activating Token Index: 524

Text #12

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5207. Min Act: -0.1700

Data Index: 1586383 (Open Web Text)

Max Activating Token Index: 966

Text #13

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5834. Min Act: -0.1700

Data Index: 5166644 (Open Web Text)

Max Activating Token Index: 104

Text #14

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5605. Min Act: -0.1700

Data Index: 7082576 (Open Web Text)

Max Activating Token Index: 55

Text #15

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5293. Min Act: -0.1700

Data Index: 4525330 (Open Web Text)

Max Activating Token Index: 272

Text #16

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5573. Min Act: -0.1700

Data Index: 6898238 (Open Web Text)

Max Activating Token Index: 871

Text #17

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5364. Min Act: -0.1700

Data Index: 6424785 (Open Web Text)

Max Activating Token Index: 499

Text #18

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5412. Min Act: -0.1700

Data Index: 4111658 (Open Web Text)

Max Activating Token Index: 442

Text #19

Max Range: 4.8624. Min Range: -4.8624

Max Act: 4.5323. Min Act: -0.1700

Data Index: 865965 (Open Web Text)

Max Activating Token Index: 914