Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2528 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6085. Min Range: -7.6085
Max Act: 7.6085. Min Act: -0.1700
Data Index: 6991778 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6085. Min Range: -7.6085
Max Act: 7.5148. Min Act: -0.1700
Data Index: 1067134 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6085. Min Range: -7.6085
Max Act: 7.0148. Min Act: -0.1700
Data Index: 3044908 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.9523. Min Act: -0.1700
Data Index: 8586076 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.8585. Min Act: -0.1700
Data Index: 6960000 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.7960. Min Act: -0.1700
Data Index: 817275 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.7648. Min Act: -0.1700
Data Index: 727058 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.7023. Min Act: -0.1700
Data Index: 3533806 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.6085. Min Act: -0.1700
Data Index: 6638920 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.6398. Min Act: -0.1700
Data Index: 2483434 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.5773. Min Act: -0.1699
Data Index: 4224082 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.5773. Min Act: -0.1700
Data Index: 3369376 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.6085. Min Act: -0.1700
Data Index: 4198640 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.5460. Min Act: -0.1700
Data Index: 5329157 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.5773. Min Act: -0.1700
Data Index: 5362622 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.5773. Min Act: -0.1700
Data Index: 1891897 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.5460. Min Act: -0.1700
Data Index: 1935713 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.5148. Min Act: -0.1700
Data Index: 6762380 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.5148. Min Act: -0.1700
Data Index: 4630716 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6085. Min Range: -7.6085
Max Act: 6.5148. Min Act: -0.1700
Data Index: 6205844 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19