Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1458 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.9870. Min Act: -0.1700
Data Index: 5955894 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.9870. Min Act: -0.1700
Data Index: 7655610 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.9245. Min Act: -0.1700
Data Index: 6316622 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.8620. Min Act: -0.1700
Data Index: 8440577 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.8620. Min Act: -0.1700
Data Index: 8696770 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.7370. Min Act: -0.1700
Data Index: 6095547 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.7370. Min Act: -0.1700
Data Index: 736557 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.7370. Min Act: -0.1700
Data Index: 2915157 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.7370. Min Act: -0.1700
Data Index: 1422532 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.7370. Min Act: -0.1700
Data Index: 3772911 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.7370. Min Act: -0.1700
Data Index: 2543366 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.6120. Min Act: -0.1700
Data Index: 8218595 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.6745. Min Act: -0.1700
Data Index: 4644973 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.7370. Min Act: -0.1700
Data Index: 8078252 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.6745. Min Act: -0.1700
Data Index: 1877805 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.6120. Min Act: -0.1700
Data Index: 2050850 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.6120. Min Act: -0.1700
Data Index: 5199607 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.5495. Min Act: -0.1700
Data Index: 3251076 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.5495. Min Act: -0.1700
Data Index: 3175983 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9870. Min Range: -9.9870
Max Act: 9.5495. Min Act: -0.1700
Data Index: 6881722 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19