Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3933 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.7102. Min Act: -0.1700
Data Index: 6119449 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.5852. Min Act: -0.1700
Data Index: 6371441 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.4290. Min Act: -0.1700
Data Index: 4428507 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.3977. Min Act: -0.1700
Data Index: 6229621 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.3665. Min Act: -0.1700
Data Index: 4499110 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.3977. Min Act: -0.1700
Data Index: 1753552 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.3040. Min Act: -0.1700
Data Index: 4174244 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.3040. Min Act: -0.1700
Data Index: 985561 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.3040. Min Act: -0.1700
Data Index: 1611244 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.2727. Min Act: -0.1700
Data Index: 5702292 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.2727. Min Act: -0.1700
Data Index: 5651989 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.2727. Min Act: -0.1700
Data Index: 6721613 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.2727. Min Act: -0.1700
Data Index: 3238503 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.2727. Min Act: -0.1700
Data Index: 8077997 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.2727. Min Act: -0.1700
Data Index: 2631223 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.2415. Min Act: -0.1700
Data Index: 5123723 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.2102. Min Act: -0.1700
Data Index: 940214 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.1790. Min Act: -0.1700
Data Index: 7160146 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.1477. Min Act: -0.1700
Data Index: 5203463 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7102. Min Range: -5.7102
Max Act: 5.1790. Min Act: -0.1700
Data Index: 1992488 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19