Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3372 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0441. Min Range: -6.0441
Max Act: 6.0441. Min Act: -0.1700
Data Index: 2328066 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.9504. Min Act: -0.1700
Data Index: 1140517 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.9191. Min Act: -0.1700
Data Index: 4916589 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.9504. Min Act: -0.1700
Data Index: 4139117 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.9191. Min Act: -0.1700
Data Index: 1081623 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.9504. Min Act: -0.1700
Data Index: 2121922 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.8879. Min Act: -0.1700
Data Index: 6452239 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.8879. Min Act: -0.1700
Data Index: 5118646 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.8879. Min Act: -0.1700
Data Index: 7532460 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.8254. Min Act: -0.1700
Data Index: 2625612 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.7941. Min Act: -0.1700
Data Index: 8378201 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.7941. Min Act: -0.1700
Data Index: 4876772 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.7941. Min Act: -0.1700
Data Index: 5782098 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.7941. Min Act: -0.1700
Data Index: 5253286 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.7941. Min Act: -0.1700
Data Index: 1011061 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.7629. Min Act: -0.1700
Data Index: 3517638 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.7941. Min Act: -0.1700
Data Index: 5930553 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.7316. Min Act: -0.1700
Data Index: 4089033 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.7316. Min Act: -0.1700
Data Index: 6949289 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0441. Min Range: -6.0441
Max Act: 5.7629. Min Act: -0.1700
Data Index: 1877752 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19