Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 817 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3302. Min Range: -6.3302
Max Act: 6.3302. Min Act: -0.1700
Data Index: 2434475 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3302. Min Range: -6.3302
Max Act: 6.2052. Min Act: -0.1700
Data Index: 6137905 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.8615. Min Act: -0.1700
Data Index: 3409631 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.8302. Min Act: -0.1700
Data Index: 1030905 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.6115. Min Act: -0.1700
Data Index: 7623993 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.6115. Min Act: -0.1700
Data Index: 2568717 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5802. Min Act: -0.1700
Data Index: 6682686 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5802. Min Act: -0.1700
Data Index: 4774041 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5802. Min Act: -0.1700
Data Index: 7529445 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5802. Min Act: -0.1700
Data Index: 4383232 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5802. Min Act: -0.1700
Data Index: 1952782 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5490. Min Act: -0.1700
Data Index: 4325991 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5802. Min Act: -0.1700
Data Index: 347590 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5490. Min Act: -0.1700
Data Index: 4768116 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5490. Min Act: -0.1700
Data Index: 2889214 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5490. Min Act: -0.1700
Data Index: 8679314 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5177. Min Act: -0.1700
Data Index: 3210974 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5177. Min Act: -0.1700
Data Index: 6509002 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5177. Min Act: -0.1700
Data Index: 6052602 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3302. Min Range: -6.3302
Max Act: 5.5177. Min Act: -0.1700
Data Index: 5664268 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19