Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4509 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.8859. Min Act: -0.1700
Data Index: 1973012 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.8547. Min Act: -0.1700
Data Index: 8714297 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.8234. Min Act: -0.1700
Data Index: 8530818 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.7452. Min Act: -0.1700
Data Index: 3833953 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.7452. Min Act: -0.1700
Data Index: 1165720 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.7452. Min Act: -0.1700
Data Index: 758774 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.7296. Min Act: -0.1700
Data Index: 220011 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.7452. Min Act: -0.1700
Data Index: 4826390 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.7139. Min Act: -0.1700
Data Index: 2003853 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.6983. Min Act: -0.1700
Data Index: 6670443 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.6983. Min Act: -0.1700
Data Index: 358740 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.6983. Min Act: -0.1700
Data Index: 3883512 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.6826. Min Act: -0.1700
Data Index: 3813653 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.6826. Min Act: -0.1700
Data Index: 2943014 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.6983. Min Act: -0.1700
Data Index: 463389 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.6513. Min Act: -0.1700
Data Index: 5747892 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.6513. Min Act: -0.1700
Data Index: 7923162 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.6357. Min Act: -0.1700
Data Index: 3608217 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.6357. Min Act: -0.1700
Data Index: 1193501 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8859. Min Range: -3.8859
Max Act: 3.6357. Min Act: -0.1700
Data Index: 715013 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19