Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2867 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.7467. Min Act: -0.1700
Data Index: 5217000 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4655. Min Act: -0.1700
Data Index: 902320 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4655. Min Act: -0.1700
Data Index: 7216234 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4342. Min Act: -0.1700
Data Index: 4857431 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4655. Min Act: -0.1700
Data Index: 5853158 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4030. Min Act: -0.1700
Data Index: 3867723 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4030. Min Act: -0.1700
Data Index: 7521107 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4030. Min Act: -0.1700
Data Index: 7430339 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4030. Min Act: -0.1700
Data Index: 6949188 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.3717. Min Act: -0.1700
Data Index: 8484998 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.4030. Min Act: -0.1700
Data Index: 4526810 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.3717. Min Act: -0.1700
Data Index: 5630964 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.3405. Min Act: -0.1700
Data Index: 5646327 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.3405. Min Act: -0.1700
Data Index: 3826405 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.3405. Min Act: -0.1700
Data Index: 7613222 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.3405. Min Act: -0.1700
Data Index: 5198299 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.3405. Min Act: -0.1700
Data Index: 6798860 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.3092. Min Act: -0.1700
Data Index: 3915385 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.2780. Min Act: -0.1700
Data Index: 85312 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7467. Min Range: -6.7467
Max Act: 6.3092. Min Act: -0.1700
Data Index: 4358725 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19