Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6395 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1577. Min Range: -4.1577
Max Act: 4.1577. Min Act: -0.1700
Data Index: 1122288 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1577. Min Range: -4.1577
Max Act: 4.1265. Min Act: -0.1700
Data Index: 3285346 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1577. Min Range: -4.1577
Max Act: 4.1265. Min Act: -0.1700
Data Index: 2633550 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1577. Min Range: -4.1577
Max Act: 4.1265. Min Act: -0.1700
Data Index: 639230 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1577. Min Range: -4.1577
Max Act: 4.0952. Min Act: -0.1700
Data Index: 2759424 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1577. Min Range: -4.1577
Max Act: 4.0640. Min Act: -0.1700
Data Index: 7945679 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1577. Min Range: -4.1577
Max Act: 4.0640. Min Act: -0.1700
Data Index: 4294831 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1577. Min Range: -4.1577
Max Act: 4.0327. Min Act: -0.1700
Data Index: 4502439 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1577. Min Range: -4.1577
Max Act: 4.0327. Min Act: -0.1700
Data Index: 422153 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1577. Min Range: -4.1577
Max Act: 4.0327. Min Act: -0.1700
Data Index: 4963760 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1577. Min Range: -4.1577
Max Act: 4.0327. Min Act: -0.1700
Data Index: 4576010 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1577. Min Range: -4.1577
Max Act: 4.0014. Min Act: -0.1700
Data Index: 5093953 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1577. Min Range: -4.1577
Max Act: 4.0014. Min Act: -0.1700
Data Index: 6448355 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1577. Min Range: -4.1577
Max Act: 3.9702. Min Act: -0.1700
Data Index: 5523484 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1577. Min Range: -4.1577
Max Act: 3.9389. Min Act: -0.1700
Data Index: 416755 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1577. Min Range: -4.1577
Max Act: 3.9389. Min Act: -0.1700
Data Index: 7999555 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1577. Min Range: -4.1577
Max Act: 3.9389. Min Act: -0.1700
Data Index: 6839457 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1577. Min Range: -4.1577
Max Act: 3.9389. Min Act: -0.1700
Data Index: 3248361 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1577. Min Range: -4.1577
Max Act: 3.9076. Min Act: -0.1700
Data Index: 5930707 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1577. Min Range: -4.1577
Max Act: 3.9076. Min Act: -0.1700
Data Index: 4385781 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19