Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4712 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5251. Min Range: -5.5251
Max Act: 5.5251. Min Act: -0.1700
Data Index: 195871 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.9626. Min Act: -0.1700
Data Index: 8558359 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.9313. Min Act: -0.1700
Data Index: 2309379 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.9001. Min Act: -0.1700
Data Index: 8486458 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.8688. Min Act: -0.1700
Data Index: 4355825 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.8376. Min Act: -0.1700
Data Index: 8129297 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.8063. Min Act: -0.1700
Data Index: 6078779 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.8376. Min Act: -0.1700
Data Index: 2792599 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.8376. Min Act: -0.1700
Data Index: 8463167 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.8063. Min Act: -0.1700
Data Index: 1154614 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.7751. Min Act: -0.1700
Data Index: 4532478 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.7438. Min Act: -0.1700
Data Index: 2481654 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.7751. Min Act: -0.1700
Data Index: 5764466 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.7751. Min Act: -0.1700
Data Index: 7736700 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.7751. Min Act: -0.1700
Data Index: 707678 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.7438. Min Act: -0.1700
Data Index: 265653 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.7438. Min Act: -0.1700
Data Index: 380205 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.7438. Min Act: -0.1700
Data Index: 817292 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.7438. Min Act: -0.1700
Data Index: 8437067 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5251. Min Range: -5.5251
Max Act: 4.7438. Min Act: -0.1700
Data Index: 2625139 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19