Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3687 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7336. Min Range: -8.7336
Max Act: 8.7336. Min Act: -0.1700
Data Index: 129474 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7336. Min Range: -8.7336
Max Act: 8.6711. Min Act: -0.1700
Data Index: 914668 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7336. Min Range: -8.7336
Max Act: 8.7336. Min Act: -0.1700
Data Index: 8431362 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7336. Min Range: -8.7336
Max Act: 8.5461. Min Act: -0.1700
Data Index: 129475 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7336. Min Range: -8.7336
Max Act: 8.4836. Min Act: -0.1700
Data Index: 1769573 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7336. Min Range: -8.7336
Max Act: 8.3586. Min Act: -0.1700
Data Index: 4898062 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7336. Min Range: -8.7336
Max Act: 8.2961. Min Act: -0.1700
Data Index: 1223087 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7336. Min Range: -8.7336
Max Act: 8.2336. Min Act: -0.1700
Data Index: 8741942 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7336. Min Range: -8.7336
Max Act: 8.2336. Min Act: -0.1700
Data Index: 2711981 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7336. Min Range: -8.7336
Max Act: 8.2336. Min Act: -0.1700
Data Index: 6078933 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7336. Min Range: -8.7336
Max Act: 8.1398. Min Act: -0.1700
Data Index: 5188657 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7336. Min Range: -8.7336
Max Act: 8.1086. Min Act: -0.1700
Data Index: 1010389 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7336. Min Range: -8.7336
Max Act: 8.0461. Min Act: -0.1700
Data Index: 8823802 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7336. Min Range: -8.7336
Max Act: 7.9836. Min Act: -0.1700
Data Index: 965835 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7336. Min Range: -8.7336
Max Act: 7.9836. Min Act: -0.1700
Data Index: 3733766 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7336. Min Range: -8.7336
Max Act: 7.9523. Min Act: -0.1700
Data Index: 2671878 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7336. Min Range: -8.7336
Max Act: 7.9211. Min Act: -0.1700
Data Index: 3880590 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7336. Min Range: -8.7336
Max Act: 7.9211. Min Act: -0.1700
Data Index: 3726260 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7336. Min Range: -8.7336
Max Act: 7.8898. Min Act: -0.1700
Data Index: 466898 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7336. Min Range: -8.7336
Max Act: 7.9211. Min Act: -0.1700
Data Index: 2074468 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19