Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3875 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.4779. Min Act: -0.1700
Data Index: 4262756 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.4779. Min Act: -0.1700
Data Index: 3018562 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.4154. Min Act: -0.1700
Data Index: 1119435 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.3216. Min Act: -0.1700
Data Index: 4114515 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.2904. Min Act: -0.1700
Data Index: 1258448 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.2279. Min Act: -0.1700
Data Index: 3885269 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.2279. Min Act: -0.1700
Data Index: 6504935 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.1966. Min Act: -0.1700
Data Index: 5011350 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.2279. Min Act: -0.1700
Data Index: 2323428 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.1966. Min Act: -0.1700
Data Index: 8549663 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.1654. Min Act: -0.1700
Data Index: 6212128 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.1029. Min Act: -0.1700
Data Index: 3973820 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.1029. Min Act: -0.1700
Data Index: 6204580 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.1029. Min Act: -0.1700
Data Index: 6587147 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.0716. Min Act: -0.1700
Data Index: 2909377 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.1029. Min Act: -0.1700
Data Index: 4958858 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.1029. Min Act: -0.1700
Data Index: 5929047 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.1029. Min Act: -0.1700
Data Index: 7204968 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.1029. Min Act: -0.1700
Data Index: 4690898 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4779. Min Range: -6.4779
Max Act: 6.0716. Min Act: -0.1700
Data Index: 7443722 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19