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

Dataset: Open Web Text

Neuron 1839 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: 3.9060. Min Range: -3.9060

Max Act: 3.9060. Min Act: -0.1700

Data Index: 3377283 (Open Web Text)

Max Activating Token Index: 438

Text #1

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.8423. Min Act: -0.1700

Data Index: 1037785 (Open Web Text)

Max Activating Token Index: 600

Text #2

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.8192. Min Act: -0.1700

Data Index: 8762540 (Open Web Text)

Max Activating Token Index: 596

Text #3

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7834. Min Act: -0.1700

Data Index: 8082478 (Open Web Text)

Max Activating Token Index: 743

Text #4

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7888. Min Act: -0.1700

Data Index: 1172804 (Open Web Text)

Max Activating Token Index: 365

Text #5

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7751. Min Act: -0.1700

Data Index: 4956590 (Open Web Text)

Max Activating Token Index: 630

Text #6

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7681. Min Act: -0.1700

Data Index: 2775689 (Open Web Text)

Max Activating Token Index: 490

Text #7

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7219. Min Act: -0.1700

Data Index: 337442 (Open Web Text)

Max Activating Token Index: 53

Text #8

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7464. Min Act: -0.1700

Data Index: 6076823 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7466. Min Act: -0.1700

Data Index: 5754272 (Open Web Text)

Max Activating Token Index: 715

Text #10

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7513. Min Act: -0.1700

Data Index: 345994 (Open Web Text)

Max Activating Token Index: 720

Text #11

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7280. Min Act: -0.1700

Data Index: 1037776 (Open Web Text)

Max Activating Token Index: 753

Text #12

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7113. Min Act: -0.1700

Data Index: 4689170 (Open Web Text)

Max Activating Token Index: 197

Text #13

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7339. Min Act: -0.1700

Data Index: 8018100 (Open Web Text)

Max Activating Token Index: 401

Text #14

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7366. Min Act: -0.1700

Data Index: 7879964 (Open Web Text)

Max Activating Token Index: 476

Text #15

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7134. Min Act: -0.1700

Data Index: 6740933 (Open Web Text)

Max Activating Token Index: 735

Text #16

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7265. Min Act: -0.1700

Data Index: 104668 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.6958. Min Act: -0.1700

Data Index: 6277307 (Open Web Text)

Max Activating Token Index: 437

Text #18

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.6814. Min Act: -0.1700

Data Index: 2113894 (Open Web Text)

Max Activating Token Index: 904

Text #19

Max Range: 3.9060. Min Range: -3.9060

Max Act: 3.7003. Min Act: -0.1700

Data Index: 3532881 (Open Web Text)

Max Activating Token Index: 533