Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6378 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.4137. Min Act: -0.1700
Data Index: 3076081 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.4137. Min Act: -0.1700
Data Index: 7268774 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.2262. Min Act: -0.1700
Data Index: 848213 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.1324. Min Act: -0.1700
Data Index: 3109814 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.0699. Min Act: -0.1700
Data Index: 6636062 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.1012. Min Act: -0.1700
Data Index: 7285016 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.0699. Min Act: -0.1700
Data Index: 5048334 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.0387. Min Act: -0.1700
Data Index: 3093906 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.0387. Min Act: -0.1700
Data Index: 3424368 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.0387. Min Act: -0.1700
Data Index: 4210434 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.0074. Min Act: -0.1700
Data Index: 8058814 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.0074. Min Act: -0.1700
Data Index: 6542139 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.0074. Min Act: -0.1700
Data Index: 5334491 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.0074. Min Act: -0.1700
Data Index: 4415732 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4137. Min Range: -6.4137
Max Act: 6.0074. Min Act: -0.1700
Data Index: 2303535 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4137. Min Range: -6.4137
Max Act: 5.9762. Min Act: -0.1700
Data Index: 2523698 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4137. Min Range: -6.4137
Max Act: 5.9762. Min Act: -0.1700
Data Index: 3109822 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4137. Min Range: -6.4137
Max Act: 5.9762. Min Act: -0.1700
Data Index: 6542138 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4137. Min Range: -6.4137
Max Act: 5.9762. Min Act: -0.1700
Data Index: 1794210 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4137. Min Range: -6.4137
Max Act: 5.9762. Min Act: -0.1700
Data Index: 5047742 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19