Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0847. Min Range: -6.0847
Max Act: 6.0847. Min Act: -0.1700
Data Index: 7793464 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.8972. Min Act: -0.1700
Data Index: 8735790 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.8972. Min Act: -0.1700
Data Index: 4596913 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.8972. Min Act: -0.1700
Data Index: 2758563 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.8659. Min Act: -0.1700
Data Index: 2024147 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.8659. Min Act: -0.1700
Data Index: 3680285 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.8347. Min Act: -0.1700
Data Index: 3441871 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.8347. Min Act: -0.1700
Data Index: 7517071 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.8034. Min Act: -0.1700
Data Index: 6236864 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.8034. Min Act: -0.1700
Data Index: 2016099 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.8034. Min Act: -0.1700
Data Index: 3188461 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.8034. Min Act: -0.1700
Data Index: 3589503 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.8034. Min Act: -0.1700
Data Index: 1042846 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.8034. Min Act: -0.1700
Data Index: 2117253 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.7722. Min Act: -0.1700
Data Index: 3708212 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.7722. Min Act: -0.1700
Data Index: 2929668 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.7722. Min Act: -0.1700
Data Index: 5232609 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.7409. Min Act: -0.1700
Data Index: 4981624 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.7722. Min Act: -0.1700
Data Index: 2860821 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0847. Min Range: -6.0847
Max Act: 5.7722. Min Act: -0.1700
Data Index: 1259992 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19