Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1809 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.7086. Min Act: -0.1700
Data Index: 7188304 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.7086. Min Act: -0.1700
Data Index: 8203758 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.7086. Min Act: -0.1700
Data Index: 1486031 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.6148. Min Act: -0.1700
Data Index: 2706309 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.6148. Min Act: -0.1700
Data Index: 5008988 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.6148. Min Act: -0.1700
Data Index: 2344075 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.6148. Min Act: -0.1700
Data Index: 2402862 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.5836. Min Act: -0.1700
Data Index: 7400546 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.6148. Min Act: -0.1700
Data Index: 6428257 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.5836. Min Act: -0.1700
Data Index: 1677499 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.5523. Min Act: -0.1700
Data Index: 7863189 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.5211. Min Act: -0.1700
Data Index: 1464224 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.5523. Min Act: -0.1700
Data Index: 4745018 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.5523. Min Act: -0.1700
Data Index: 3763230 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.5523. Min Act: -0.1700
Data Index: 2352807 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.5523. Min Act: -0.1700
Data Index: 489127 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.5523. Min Act: -0.1700
Data Index: 7171790 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.4898. Min Act: -0.1700
Data Index: 7387716 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.5211. Min Act: -0.1700
Data Index: 2400094 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7086. Min Range: -6.7086
Max Act: 6.5211. Min Act: -0.1700
Data Index: 1476289 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19