Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.3958. Min Act: -0.1700
Data Index: 6238533 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.2083. Min Act: -0.1700
Data Index: 4853354 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.0833. Min Act: -0.1700
Data Index: 520320 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3958. Min Range: -6.3958
Max Act: 6.0521. Min Act: -0.1700
Data Index: 6722583 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.9271. Min Act: -0.1700
Data Index: 4500964 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.8646. Min Act: -0.1700
Data Index: 3131080 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.8333. Min Act: -0.1700
Data Index: 3912026 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.8021. Min Act: -0.1700
Data Index: 2326393 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.7708. Min Act: -0.1700
Data Index: 3912025 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.7708. Min Act: -0.1700
Data Index: 3131079 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.7708. Min Act: -0.1700
Data Index: 5305855 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.7396. Min Act: -0.1700
Data Index: 8258747 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.7083. Min Act: -0.1700
Data Index: 820880 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.7083. Min Act: -0.1700
Data Index: 4426307 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.7396. Min Act: -0.1700
Data Index: 1717287 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.7083. Min Act: -0.1700
Data Index: 530945 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.7083. Min Act: -0.1700
Data Index: 5212304 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.6771. Min Act: -0.1700
Data Index: 8512486 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.6458. Min Act: -0.1700
Data Index: 3228033 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3958. Min Range: -6.3958
Max Act: 5.6458. Min Act: -0.1700
Data Index: 3889168 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19