Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4467 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6598. Min Range: -7.6598
Max Act: 7.6598. Min Act: -0.1700
Data Index: 2333762 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6598. Min Range: -7.6598
Max Act: 7.5973. Min Act: -0.1700
Data Index: 7086207 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6598. Min Range: -7.6598
Max Act: 7.2223. Min Act: -0.1700
Data Index: 7366041 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6598. Min Range: -7.6598
Max Act: 7.0036. Min Act: -0.1700
Data Index: 7669907 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.9723. Min Act: -0.1700
Data Index: 5544201 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.9098. Min Act: -0.1700
Data Index: 6330653 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.9098. Min Act: -0.1700
Data Index: 14550 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.8786. Min Act: -0.1700
Data Index: 8064057 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.8473. Min Act: -0.1700
Data Index: 1106803 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.8161. Min Act: -0.1700
Data Index: 4974252 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.7848. Min Act: -0.1700
Data Index: 2611913 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.7848. Min Act: -0.1700
Data Index: 5298172 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.7536. Min Act: -0.1700
Data Index: 3055928 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.7536. Min Act: -0.1700
Data Index: 4680979 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.7223. Min Act: -0.1700
Data Index: 3528261 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.6911. Min Act: -0.1700
Data Index: 3656687 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.6598. Min Act: -0.1700
Data Index: 677151 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.6598. Min Act: -0.1700
Data Index: 4665546 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.6598. Min Act: -0.1700
Data Index: 4540437 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6598. Min Range: -7.6598
Max Act: 6.5973. Min Act: -0.1700
Data Index: 26155 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19