Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3784 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.7569. Min Act: -0.1700
Data Index: 4944461 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.7569. Min Act: -0.1700
Data Index: 2185769 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.7256. Min Act: -0.1700
Data Index: 3270203 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.7256. Min Act: -0.1700
Data Index: 365932 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.7256. Min Act: -0.1700
Data Index: 8786574 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.7256. Min Act: -0.1700
Data Index: 6553935 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.6631. Min Act: -0.1700
Data Index: 1324904 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.6319. Min Act: -0.1700
Data Index: 424507 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.6319. Min Act: -0.1700
Data Index: 1897587 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.6006. Min Act: -0.1700
Data Index: 2617591 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.5694. Min Act: -0.1700
Data Index: 5598513 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.5381. Min Act: -0.1700
Data Index: 6159883 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.5381. Min Act: -0.1700
Data Index: 8100111 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.5381. Min Act: -0.1700
Data Index: 7308711 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.5069. Min Act: -0.1700
Data Index: 882337 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.5069. Min Act: -0.1700
Data Index: 5262768 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.5069. Min Act: -0.1700
Data Index: 6094369 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.4756. Min Act: -0.1700
Data Index: 1194031 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.4756. Min Act: -0.1700
Data Index: 2430546 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7569. Min Range: -5.7569
Max Act: 5.4756. Min Act: -0.1700
Data Index: 4619342 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19