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

Dataset: Open Web Text

Neuron 1974 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: 5.1458. Min Range: -5.1458

Max Act: 5.1458. Min Act: -0.1700

Data Index: 2606481 (Open Web Text)

Max Activating Token Index: 503

Text #1

Max Range: 5.1458. Min Range: -5.1458

Max Act: 5.0604. Min Act: -0.1700

Data Index: 4464455 (Open Web Text)

Max Activating Token Index: 293

Text #2

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.9925. Min Act: -0.1700

Data Index: 3800954 (Open Web Text)

Max Activating Token Index: 350

Text #3

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.9604. Min Act: -0.1700

Data Index: 4901138 (Open Web Text)

Max Activating Token Index: 472

Text #4

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.9327. Min Act: -0.1700

Data Index: 1772599 (Open Web Text)

Max Activating Token Index: 80

Text #5

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.9071. Min Act: -0.1700

Data Index: 3874540 (Open Web Text)

Max Activating Token Index: 421

Text #6

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.8942. Min Act: -0.1700

Data Index: 8608045 (Open Web Text)

Max Activating Token Index: 28

Text #7

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.8544. Min Act: -0.1700

Data Index: 8813747 (Open Web Text)

Max Activating Token Index: 669

Text #8

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.8753. Min Act: -0.1700

Data Index: 8643439 (Open Web Text)

Max Activating Token Index: 831

Text #9

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.8679. Min Act: -0.1700

Data Index: 836227 (Open Web Text)

Max Activating Token Index: 619

Text #10

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.8565. Min Act: -0.1700

Data Index: 3982102 (Open Web Text)

Max Activating Token Index: 577

Text #11

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.8323. Min Act: -0.1700

Data Index: 2015933 (Open Web Text)

Max Activating Token Index: 255

Text #12

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.8040. Min Act: -0.1700

Data Index: 3216066 (Open Web Text)

Max Activating Token Index: 80

Text #13

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.8227. Min Act: -0.1700

Data Index: 5785586 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.8181. Min Act: -0.1700

Data Index: 6496745 (Open Web Text)

Max Activating Token Index: 328

Text #15

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.8025. Min Act: -0.1700

Data Index: 3745908 (Open Web Text)

Max Activating Token Index: 648

Text #16

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.7822. Min Act: -0.1700

Data Index: 6805503 (Open Web Text)

Max Activating Token Index: 225

Text #17

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.8005. Min Act: -0.1700

Data Index: 6805502 (Open Web Text)

Max Activating Token Index: 29

Text #18

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.8052. Min Act: -0.1700

Data Index: 622163 (Open Web Text)

Max Activating Token Index: 692

Text #19

Max Range: 5.1458. Min Range: -5.1458

Max Act: 4.8209. Min Act: -0.1700

Data Index: 4425640 (Open Web Text)

Max Activating Token Index: 341