Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1983 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0197. Min Range: -5.0197
Max Act: 5.0197. Min Act: -0.1700
Data Index: 5659945 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.8322. Min Act: -0.1700
Data Index: 5747327 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.7697. Min Act: -0.1700
Data Index: 6027517 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.8009. Min Act: -0.1700
Data Index: 544848 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.7697. Min Act: -0.1700
Data Index: 2328693 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.7697. Min Act: -0.1700
Data Index: 2223471 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.7072. Min Act: -0.1700
Data Index: 954804 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.7072. Min Act: -0.1700
Data Index: 5536465 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.7072. Min Act: -0.1700
Data Index: 6256025 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.7384. Min Act: -0.1700
Data Index: 4362837 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.7072. Min Act: -0.1700
Data Index: 941950 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.7072. Min Act: -0.1700
Data Index: 5256774 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.7072. Min Act: -0.1700
Data Index: 8652074 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.7072. Min Act: -0.1700
Data Index: 6231005 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.6759. Min Act: -0.1700
Data Index: 3452659 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.6447. Min Act: -0.1700
Data Index: 8008526 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.6759. Min Act: -0.1700
Data Index: 2328692 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.6759. Min Act: -0.1700
Data Index: 8139814 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.6134. Min Act: -0.1700
Data Index: 8004913 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0197. Min Range: -5.0197
Max Act: 4.6759. Min Act: -0.1700
Data Index: 2960166 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19