Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1951 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.8164. Min Act: -0.1700
Data Index: 5806252 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.7539. Min Act: -0.1700
Data Index: 4278007 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.7539. Min Act: -0.1700
Data Index: 4960599 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.5664. Min Act: -0.1700
Data Index: 1304670 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.5664. Min Act: -0.1700
Data Index: 1136301 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.5664. Min Act: -0.1700
Data Index: 8456833 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.5039. Min Act: -0.1700
Data Index: 1268725 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.4414. Min Act: -0.1700
Data Index: 8083639 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.4414. Min Act: -0.1700
Data Index: 3241064 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.3164. Min Act: -0.1700
Data Index: 6548963 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.3789. Min Act: -0.1700
Data Index: 3022225 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.3789. Min Act: -0.1700
Data Index: 1915626 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.3164. Min Act: -0.1700
Data Index: 751678 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.3164. Min Act: -0.1700
Data Index: 4668223 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.3164. Min Act: -0.1700
Data Index: 2536502 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.3164. Min Act: -0.1700
Data Index: 2530112 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.3164. Min Act: -0.1700
Data Index: 411834 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.3164. Min Act: -0.1700
Data Index: 7640458 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.2539. Min Act: -0.1700
Data Index: 6972812 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8164. Min Range: -10.8164
Max Act: 10.2539. Min Act: -0.1700
Data Index: 1950590 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19