Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3379. Min Range: -8.3379
Max Act: 8.3379. Min Act: -0.1700
Data Index: 994932 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3379. Min Range: -8.3379
Max Act: 8.0879. Min Act: -0.1700
Data Index: 1332426 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.9629. Min Act: -0.1700
Data Index: 664212 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.9004. Min Act: -0.1700
Data Index: 867257 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.9004. Min Act: -0.1700
Data Index: 162266 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.9004. Min Act: -0.1700
Data Index: 8331671 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.8379. Min Act: -0.1700
Data Index: 5110728 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.7754. Min Act: -0.1700
Data Index: 3165633 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.7129. Min Act: -0.1700
Data Index: 3352356 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.6504. Min Act: -0.1700
Data Index: 8689241 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.6504. Min Act: -0.1700
Data Index: 1810933 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.6504. Min Act: -0.1700
Data Index: 6130655 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.6504. Min Act: -0.1700
Data Index: 3908842 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.5879. Min Act: -0.1700
Data Index: 6288113 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.5879. Min Act: -0.1700
Data Index: 4776034 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.5254. Min Act: -0.1700
Data Index: 7756533 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.5879. Min Act: -0.1700
Data Index: 5815253 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.5879. Min Act: -0.1700
Data Index: 780532 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.5879. Min Act: -0.1700
Data Index: 3293583 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3379. Min Range: -8.3379
Max Act: 7.5879. Min Act: -0.1700
Data Index: 4685532 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19