Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2667 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1861. Min Range: -7.1861
Max Act: 7.1861. Min Act: -0.1700
Data Index: 4385189 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.9673. Min Act: -0.1700
Data Index: 2672867 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.8736. Min Act: -0.1700
Data Index: 7919051 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.7486. Min Act: -0.1700
Data Index: 4128552 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.6861. Min Act: -0.1700
Data Index: 37301 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.5923. Min Act: -0.1700
Data Index: 6509691 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.5611. Min Act: -0.1700
Data Index: 8058620 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.5298. Min Act: -0.1700
Data Index: 1678891 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.5611. Min Act: -0.1700
Data Index: 634135 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.5298. Min Act: -0.1700
Data Index: 7951439 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.4986. Min Act: -0.1700
Data Index: 4145958 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.4986. Min Act: -0.1700
Data Index: 4444547 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.4986. Min Act: -0.1700
Data Index: 8694124 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.4673. Min Act: -0.1700
Data Index: 4309630 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.4673. Min Act: -0.1700
Data Index: 2456235 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.4361. Min Act: -0.1700
Data Index: 4592420 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.4361. Min Act: -0.1700
Data Index: 6591110 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.4673. Min Act: -0.1700
Data Index: 6558900 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.4048. Min Act: -0.1700
Data Index: 6825221 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1861. Min Range: -7.1861
Max Act: 6.4048. Min Act: -0.1700
Data Index: 2591623 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19