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

Dataset: Open Web Text

Neuron 1804 in Layer 6

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: 3.8658. Min Range: -3.8658

Max Act: 3.8658. Min Act: -0.1700

Data Index: 3581614 (Open Web Text)

Max Activating Token Index: 634

Text #1

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.8364. Min Act: -0.1700

Data Index: 6073836 (Open Web Text)

Max Activating Token Index: 768

Text #2

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.8540. Min Act: -0.1700

Data Index: 3218600 (Open Web Text)

Max Activating Token Index: 510

Text #3

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.8057. Min Act: -0.1700

Data Index: 1580407 (Open Web Text)

Max Activating Token Index: 684

Text #4

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.8211. Min Act: -0.1700

Data Index: 3028792 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.8066. Min Act: -0.1700

Data Index: 8572304 (Open Web Text)

Max Activating Token Index: 745

Text #6

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.7761. Min Act: -0.1700

Data Index: 7685757 (Open Web Text)

Max Activating Token Index: 527

Text #7

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.7386. Min Act: -0.1700

Data Index: 431299 (Open Web Text)

Max Activating Token Index: 85

Text #8

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.7181. Min Act: -0.1700

Data Index: 423964 (Open Web Text)

Max Activating Token Index: 201

Text #9

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.7272. Min Act: -0.1700

Data Index: 5290865 (Open Web Text)

Max Activating Token Index: 966

Text #10

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.7057. Min Act: -0.1700

Data Index: 3588298 (Open Web Text)

Max Activating Token Index: 94

Text #11

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.6689. Min Act: -0.1700

Data Index: 7632799 (Open Web Text)

Max Activating Token Index: 535

Text #12

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.6883. Min Act: -0.1700

Data Index: 6503497 (Open Web Text)

Max Activating Token Index: 635

Text #13

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.6926. Min Act: -0.1700

Data Index: 7268961 (Open Web Text)

Max Activating Token Index: 87

Text #14

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.6927. Min Act: -0.1700

Data Index: 5341683 (Open Web Text)

Max Activating Token Index: 47

Text #15

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.6571. Min Act: -0.1700

Data Index: 7817530 (Open Web Text)

Max Activating Token Index: 63

Text #16

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.6508. Min Act: -0.1700

Data Index: 5957334 (Open Web Text)

Max Activating Token Index: 127

Text #17

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.6707. Min Act: -0.1700

Data Index: 2662098 (Open Web Text)

Max Activating Token Index: 159

Text #18

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.6547. Min Act: -0.1700

Data Index: 2951449 (Open Web Text)

Max Activating Token Index: 627

Text #19

Max Range: 3.8658. Min Range: -3.8658

Max Act: 3.6426. Min Act: -0.1700

Data Index: 674422 (Open Web Text)

Max Activating Token Index: 442