Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3225 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.6872. Min Act: -0.1700
Data Index: 5493485 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.5934. Min Act: -0.1700
Data Index: 491103 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.5622. Min Act: -0.1700
Data Index: 3596871 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.5309. Min Act: -0.1700
Data Index: 1112984 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.5309. Min Act: -0.1700
Data Index: 1268004 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.4997. Min Act: -0.1700
Data Index: 3608013 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.4684. Min Act: -0.1700
Data Index: 8273014 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.4684. Min Act: -0.1700
Data Index: 5098361 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.4372. Min Act: -0.1700
Data Index: 3704352 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.4059. Min Act: -0.1700
Data Index: 3789789 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.4059. Min Act: -0.1700
Data Index: 5305393 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.4059. Min Act: -0.1700
Data Index: 3189395 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.4059. Min Act: -0.1700
Data Index: 8521684 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.4059. Min Act: -0.1700
Data Index: 2155221 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.4059. Min Act: -0.1700
Data Index: 14691 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.3747. Min Act: -0.1700
Data Index: 4685726 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.3434. Min Act: -0.1700
Data Index: 8816814 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.3434. Min Act: -0.1700
Data Index: 7347485 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.3434. Min Act: -0.1700
Data Index: 6109041 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6872. Min Range: -6.6872
Max Act: 6.3434. Min Act: -0.1700
Data Index: 3614348 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19