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

Dataset: Open Web Text

Neuron 2642 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: 3.3602. Min Range: -3.3602

Max Act: 3.3602. Min Act: -0.1700

Data Index: 5527335 (Open Web Text)

Max Activating Token Index: 838

Text #1

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.2964. Min Act: -0.1700

Data Index: 7362894 (Open Web Text)

Max Activating Token Index: 362

Text #2

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.2585. Min Act: -0.1700

Data Index: 4242347 (Open Web Text)

Max Activating Token Index: 25

Text #3

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.2062. Min Act: -0.1700

Data Index: 3895973 (Open Web Text)

Max Activating Token Index: 944

Text #4

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1807. Min Act: -0.1700

Data Index: 1260764 (Open Web Text)

Max Activating Token Index: 767

Text #5

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.2003. Min Act: -0.1700

Data Index: 3692700 (Open Web Text)

Max Activating Token Index: 1005

Text #6

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1808. Min Act: -0.1700

Data Index: 3974336 (Open Web Text)

Max Activating Token Index: 420

Text #7

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1752. Min Act: -0.1700

Data Index: 3916590 (Open Web Text)

Max Activating Token Index: 362

Text #8

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1722. Min Act: -0.1700

Data Index: 7566198 (Open Web Text)

Max Activating Token Index: 341

Text #9

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1585. Min Act: -0.1700

Data Index: 8614372 (Open Web Text)

Max Activating Token Index: 401

Text #10

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1522. Min Act: -0.1700

Data Index: 4205195 (Open Web Text)

Max Activating Token Index: 71

Text #11

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1803. Min Act: -0.1700

Data Index: 5828061 (Open Web Text)

Max Activating Token Index: 501

Text #12

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1546. Min Act: -0.1700

Data Index: 5008973 (Open Web Text)

Max Activating Token Index: 619

Text #13

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1791. Min Act: -0.1700

Data Index: 75698 (Open Web Text)

Max Activating Token Index: 488

Text #14

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1724. Min Act: -0.1700

Data Index: 5930719 (Open Web Text)

Max Activating Token Index: 712

Text #15

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1409. Min Act: -0.1700

Data Index: 5061508 (Open Web Text)

Max Activating Token Index: 563

Text #16

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1270. Min Act: -0.1700

Data Index: 7491446 (Open Web Text)

Max Activating Token Index: 594

Text #17

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1549. Min Act: -0.1700

Data Index: 4264814 (Open Web Text)

Max Activating Token Index: 522

Text #18

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1368. Min Act: -0.1700

Data Index: 6361168 (Open Web Text)

Max Activating Token Index: 638

Text #19

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1391. Min Act: -0.1700

Data Index: 6009058 (Open Web Text)

Max Activating Token Index: 1004