Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3549. Min Range: -7.3549
Max Act: 7.3549. Min Act: -0.1700
Data Index: 2371784 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3549. Min Range: -7.3549
Max Act: 7.1361. Min Act: -0.1700
Data Index: 2515317 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3549. Min Range: -7.3549
Max Act: 7.0736. Min Act: -0.1700
Data Index: 6790078 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3549. Min Range: -7.3549
Max Act: 7.0736. Min Act: -0.1700
Data Index: 2217076 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.9799. Min Act: -0.1700
Data Index: 3855000 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3549. Min Range: -7.3549
Max Act: 7.0111. Min Act: -0.1700
Data Index: 8033575 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3549. Min Range: -7.3549
Max Act: 7.0424. Min Act: -0.1700
Data Index: 986660 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.9799. Min Act: -0.1700
Data Index: 8050769 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.9799. Min Act: -0.1700
Data Index: 577593 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.9799. Min Act: -0.1700
Data Index: 5674421 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.9486. Min Act: -0.1700
Data Index: 3823373 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.9486. Min Act: -0.1700
Data Index: 5094643 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.9486. Min Act: -0.1700
Data Index: 2072117 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.9174. Min Act: -0.1700
Data Index: 6513473 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.8236. Min Act: -0.1700
Data Index: 2938358 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.8861. Min Act: -0.1700
Data Index: 986661 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.8549. Min Act: -0.1700
Data Index: 4540621 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.8549. Min Act: -0.1700
Data Index: 1648327 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.8549. Min Act: -0.1700
Data Index: 2447933 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3549. Min Range: -7.3549
Max Act: 6.8236. Min Act: -0.1700
Data Index: 5856539 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19