Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5268 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.5445. Min Act: -0.1700
Data Index: 8815626 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.3570. Min Act: -0.1700
Data Index: 6869960 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.2945. Min Act: -0.1700
Data Index: 6215718 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.1070. Min Act: -0.1700
Data Index: 5750416 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.0758. Min Act: -0.1700
Data Index: 6230840 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.0445. Min Act: -0.1700
Data Index: 698118 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.0133. Min Act: -0.1700
Data Index: 6033543 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.0133. Min Act: -0.1700
Data Index: 3489149 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5445. Min Range: -6.5445
Max Act: 5.9820. Min Act: -0.1700
Data Index: 3489150 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5445. Min Range: -6.5445
Max Act: 5.9820. Min Act: -0.1700
Data Index: 1465561 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5445. Min Range: -6.5445
Max Act: 5.9820. Min Act: -0.1700
Data Index: 8815622 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5445. Min Range: -6.5445
Max Act: 5.9820. Min Act: -0.1700
Data Index: 4931220 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5445. Min Range: -6.5445
Max Act: 5.9508. Min Act: -0.1700
Data Index: 7844411 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5445. Min Range: -6.5445
Max Act: 5.9195. Min Act: -0.1700
Data Index: 6785957 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5445. Min Range: -6.5445
Max Act: 5.9195. Min Act: -0.1700
Data Index: 5450752 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5445. Min Range: -6.5445
Max Act: 5.8258. Min Act: -0.1700
Data Index: 763345 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5445. Min Range: -6.5445
Max Act: 5.8570. Min Act: -0.1700
Data Index: 8815615 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5445. Min Range: -6.5445
Max Act: 5.8258. Min Act: -0.1700
Data Index: 4372518 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5445. Min Range: -6.5445
Max Act: 5.8258. Min Act: -0.1700
Data Index: 2781816 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5445. Min Range: -6.5445
Max Act: 5.8258. Min Act: -0.1700
Data Index: 8815623 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19