Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6103 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0782. Min Range: -6.0782
Max Act: 6.0782. Min Act: -0.1700
Data Index: 2471235 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0782. Min Range: -6.0782
Max Act: 6.0782. Min Act: -0.1700
Data Index: 6700258 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0782. Min Range: -6.0782
Max Act: 6.0157. Min Act: -0.1700
Data Index: 449014 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0782. Min Range: -6.0782
Max Act: 6.0469. Min Act: -0.1700
Data Index: 569389 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.9844. Min Act: -0.1700
Data Index: 7571126 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.9844. Min Act: -0.1700
Data Index: 5312969 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.9844. Min Act: -0.1700
Data Index: 2223121 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.9844. Min Act: -0.1700
Data Index: 2486390 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.9532. Min Act: -0.1700
Data Index: 4664913 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.8907. Min Act: -0.1700
Data Index: 5645748 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.8907. Min Act: -0.1700
Data Index: 7436682 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.8907. Min Act: -0.1700
Data Index: 310657 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.8594. Min Act: -0.1700
Data Index: 1505392 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.8907. Min Act: -0.1700
Data Index: 2471237 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.8282. Min Act: -0.1700
Data Index: 2643329 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.8282. Min Act: -0.1700
Data Index: 1395416 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.7969. Min Act: -0.1700
Data Index: 2486389 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.8594. Min Act: -0.1700
Data Index: 163 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.8282. Min Act: -0.1700
Data Index: 1395414 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0782. Min Range: -6.0782
Max Act: 5.8282. Min Act: -0.1700
Data Index: 6312601 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19