Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1448 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0452. Min Range: -5.0452
Max Act: 5.0452. Min Act: -0.1700
Data Index: 4644432 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.9514. Min Act: -0.1700
Data Index: 4781197 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.9202. Min Act: -0.1700
Data Index: 4456578 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.8264. Min Act: -0.1700
Data Index: 166916 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.7014. Min Act: -0.1700
Data Index: 1923334 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.6702. Min Act: -0.1700
Data Index: 8721067 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.7014. Min Act: -0.1700
Data Index: 1585586 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.7014. Min Act: -0.1700
Data Index: 4611696 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.7014. Min Act: -0.1700
Data Index: 5235865 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.6389. Min Act: -0.1700
Data Index: 2846730 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.6389. Min Act: -0.1700
Data Index: 146257 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.6389. Min Act: -0.1700
Data Index: 4968516 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.6389. Min Act: -0.1700
Data Index: 3213867 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.6389. Min Act: -0.1700
Data Index: 5550469 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.5764. Min Act: -0.1700
Data Index: 1557404 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.6077. Min Act: -0.1700
Data Index: 1564691 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.5764. Min Act: -0.1700
Data Index: 4028612 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.6077. Min Act: -0.1700
Data Index: 7905438 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.5764. Min Act: -0.1700
Data Index: 4283606 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0452. Min Range: -5.0452
Max Act: 4.5764. Min Act: -0.1700
Data Index: 594221 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19