Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0028. Min Range: -4.0028
Max Act: 4.0028. Min Act: -0.1700
Data Index: 3394909 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.9090. Min Act: -0.1700
Data Index: 6939666 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.9090. Min Act: -0.1700
Data Index: 5104297 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8778. Min Act: -0.1700
Data Index: 524224 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8778. Min Act: -0.1700
Data Index: 6109329 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8778. Min Act: -0.1700
Data Index: 4992132 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8778. Min Act: -0.1700
Data Index: 8722810 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8465. Min Act: -0.1700
Data Index: 3739038 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8152. Min Act: -0.1700
Data Index: 524230 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.7839. Min Act: -0.1700
Data Index: 251324 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8465. Min Act: -0.1700
Data Index: 6575686 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8465. Min Act: -0.1700
Data Index: 442301 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8152. Min Act: -0.1700
Data Index: 6224153 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8152. Min Act: -0.1700
Data Index: 2681493 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8152. Min Act: -0.1700
Data Index: 7774687 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8152. Min Act: -0.1700
Data Index: 976694 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8152. Min Act: -0.1700
Data Index: 1957767 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8152. Min Act: -0.1700
Data Index: 5047393 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.8465. Min Act: -0.1700
Data Index: 3625134 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0028. Min Range: -4.0028
Max Act: 3.7839. Min Act: -0.1700
Data Index: 4992131 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19