Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4296 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.6056. Min Act: -0.1700
Data Index: 6343384 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.6056. Min Act: -0.1700
Data Index: 7812549 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.5743. Min Act: -0.1700
Data Index: 34069 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.5743. Min Act: -0.1700
Data Index: 3027215 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.3243. Min Act: -0.1700
Data Index: 3938722 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.3243. Min Act: -0.1700
Data Index: 515704 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.2931. Min Act: -0.1700
Data Index: 3264642 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.2618. Min Act: -0.1700
Data Index: 4274238 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.2618. Min Act: -0.1700
Data Index: 2012224 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.2931. Min Act: -0.1700
Data Index: 5018270 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.2618. Min Act: -0.1700
Data Index: 8088311 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.2618. Min Act: -0.1700
Data Index: 5824311 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.2306. Min Act: -0.1700
Data Index: 5097117 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.2306. Min Act: -0.1700
Data Index: 1014777 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.1993. Min Act: -0.1700
Data Index: 2427186 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.1993. Min Act: -0.1700
Data Index: 912480 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.1681. Min Act: -0.1700
Data Index: 3973470 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.1681. Min Act: -0.1700
Data Index: 1022489 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.1681. Min Act: -0.1700
Data Index: 7463357 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6056. Min Range: -6.6056
Max Act: 6.1681. Min Act: -0.1700
Data Index: 6829130 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19