Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2877 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4635. Min Range: -6.4635
Max Act: 6.4635. Min Act: -0.1700
Data Index: 3114928 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4635. Min Range: -6.4635
Max Act: 6.2135. Min Act: -0.1700
Data Index: 3939226 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4635. Min Range: -6.4635
Max Act: 6.1510. Min Act: -0.1700
Data Index: 4354080 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4635. Min Range: -6.4635
Max Act: 6.1510. Min Act: -0.1700
Data Index: 3155593 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4635. Min Range: -6.4635
Max Act: 6.0260. Min Act: -0.1700
Data Index: 4113932 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4635. Min Range: -6.4635
Max Act: 6.0573. Min Act: -0.1700
Data Index: 638735 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.9948. Min Act: -0.1700
Data Index: 4113930 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.9010. Min Act: -0.1700
Data Index: 4936684 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.9010. Min Act: -0.1700
Data Index: 3531103 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.8698. Min Act: -0.1700
Data Index: 5366700 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.8385. Min Act: -0.1700
Data Index: 3267926 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.8385. Min Act: -0.1700
Data Index: 7665684 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.8073. Min Act: -0.1700
Data Index: 124876 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.8073. Min Act: -0.1700
Data Index: 517649 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.8073. Min Act: -0.1700
Data Index: 8683674 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.8073. Min Act: -0.1700
Data Index: 1618294 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.7760. Min Act: -0.1700
Data Index: 3228569 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.7135. Min Act: -0.1700
Data Index: 5439544 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.7135. Min Act: -0.1700
Data Index: 3155594 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4635. Min Range: -6.4635
Max Act: 5.6823. Min Act: -0.1700
Data Index: 704748 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19