Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2065 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6239. Min Range: -8.6239
Max Act: 8.6239. Min Act: -0.1700
Data Index: 8282360 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.8426. Min Act: -0.1700
Data Index: 3590868 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.6239. Min Act: -0.1700
Data Index: 6326672 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.5926. Min Act: -0.1700
Data Index: 3103332 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.5614. Min Act: -0.1700
Data Index: 4534234 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.5614. Min Act: -0.1700
Data Index: 8396740 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.5614. Min Act: -0.1700
Data Index: 2442509 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.5301. Min Act: -0.1700
Data Index: 3743120 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.4989. Min Act: -0.1700
Data Index: 1491514 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.4676. Min Act: -0.1700
Data Index: 5674293 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.4676. Min Act: -0.1700
Data Index: 2399816 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.4676. Min Act: -0.1700
Data Index: 2962273 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.4051. Min Act: -0.1700
Data Index: 5129568 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.3739. Min Act: -0.1700
Data Index: 8289718 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.4051. Min Act: -0.1700
Data Index: 3091377 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.4051. Min Act: -0.1700
Data Index: 8588536 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.3739. Min Act: -0.1700
Data Index: 7834648 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.3426. Min Act: -0.1700
Data Index: 4713927 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.3426. Min Act: -0.1700
Data Index: 6247558 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6239. Min Range: -8.6239
Max Act: 7.3426. Min Act: -0.1700
Data Index: 6308003 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19