Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3743 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.8341. Min Act: -0.1700
Data Index: 2935686 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.8341. Min Act: -0.1700
Data Index: 8128792 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.7091. Min Act: -0.1700
Data Index: 6461360 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.6466. Min Act: -0.1700
Data Index: 6253613 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.5841. Min Act: -0.1700
Data Index: 2882068 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.5841. Min Act: -0.1700
Data Index: 6117723 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.3966. Min Act: -0.1700
Data Index: 6146448 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.3966. Min Act: -0.1700
Data Index: 129271 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.3341. Min Act: -0.1700
Data Index: 7515645 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.3341. Min Act: -0.1700
Data Index: 3243208 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.3966. Min Act: -0.1700
Data Index: 7805388 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.3341. Min Act: -0.1700
Data Index: 4215153 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.3341. Min Act: -0.1700
Data Index: 7370788 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.2716. Min Act: -0.1700
Data Index: 5713812 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.2716. Min Act: -0.1700
Data Index: 2375911 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.2716. Min Act: -0.1700
Data Index: 4788673 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.2716. Min Act: -0.1700
Data Index: 5280103 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.2716. Min Act: -0.1700
Data Index: 2336084 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.2716. Min Act: -0.1700
Data Index: 6190862 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8341. Min Range: -8.8341
Max Act: 8.2091. Min Act: -0.1700
Data Index: 1372607 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19