Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1765 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1653. Min Range: -6.1653
Max Act: 6.1653. Min Act: -0.1700
Data Index: 1863449 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1653. Min Range: -6.1653
Max Act: 6.1653. Min Act: -0.1700
Data Index: 2998442 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1653. Min Range: -6.1653
Max Act: 6.0716. Min Act: -0.1700
Data Index: 2588974 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1653. Min Range: -6.1653
Max Act: 6.0716. Min Act: -0.1700
Data Index: 6359498 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.9778. Min Act: -0.1700
Data Index: 4206412 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.9778. Min Act: -0.1700
Data Index: 4132438 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.9153. Min Act: -0.1700
Data Index: 3128258 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.9153. Min Act: -0.1700
Data Index: 7798206 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.9778. Min Act: -0.1700
Data Index: 5653640 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.9466. Min Act: -0.1700
Data Index: 7065367 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.9466. Min Act: -0.1700
Data Index: 4853678 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.9153. Min Act: -0.1700
Data Index: 3496176 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.9153. Min Act: -0.1700
Data Index: 5280087 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.8841. Min Act: -0.1700
Data Index: 5306410 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.9153. Min Act: -0.1700
Data Index: 6065057 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.9466. Min Act: -0.1700
Data Index: 7836495 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.9153. Min Act: -0.1700
Data Index: 3278567 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.9153. Min Act: -0.1700
Data Index: 4379562 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.8841. Min Act: -0.1700
Data Index: 3791952 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1653. Min Range: -6.1653
Max Act: 5.8841. Min Act: -0.1700
Data Index: 6202768 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19