Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 905 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1130. Min Range: -7.1130
Max Act: 7.0818. Min Act: -0.1700
Data Index: 2239816 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1130. Min Range: -7.1130
Max Act: 7.1130. Min Act: -0.1700
Data Index: 7057686 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1130. Min Range: -7.1130
Max Act: 7.0193. Min Act: -0.1700
Data Index: 6101562 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.9880. Min Act: -0.1700
Data Index: 755431 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.9568. Min Act: -0.1700
Data Index: 969552 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.9568. Min Act: -0.1700
Data Index: 7485955 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.9568. Min Act: -0.1700
Data Index: 5981996 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.9568. Min Act: -0.1700
Data Index: 7544038 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.9255. Min Act: -0.1700
Data Index: 7980500 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.9255. Min Act: -0.1700
Data Index: 5183764 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.8318. Min Act: -0.1700
Data Index: 8391039 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.8318. Min Act: -0.1700
Data Index: 3732941 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.8005. Min Act: -0.1700
Data Index: 6052562 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.8005. Min Act: -0.1700
Data Index: 3562126 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.7068. Min Act: -0.1700
Data Index: 5121672 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.6755. Min Act: -0.1700
Data Index: 3584074 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.6755. Min Act: -0.1700
Data Index: 7100478 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.6755. Min Act: -0.1700
Data Index: 8402881 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.6443. Min Act: -0.1700
Data Index: 8612424 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1130. Min Range: -7.1130
Max Act: 6.6443. Min Act: -0.1700
Data Index: 1640008 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19