Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 877 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0186. Min Range: -6.0186
Max Act: 6.0186. Min Act: -0.1700
Data Index: 1467119 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.9873. Min Act: -0.1700
Data Index: 5583629 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.8311. Min Act: -0.1700
Data Index: 7931707 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.8311. Min Act: -0.1700
Data Index: 5376074 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.7686. Min Act: -0.1700
Data Index: 8188208 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.7998. Min Act: -0.1700
Data Index: 6464271 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.7686. Min Act: -0.1700
Data Index: 6945561 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.7686. Min Act: -0.1700
Data Index: 2249058 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.7373. Min Act: -0.1700
Data Index: 1297994 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.7373. Min Act: -0.1700
Data Index: 6605894 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.7061. Min Act: -0.1700
Data Index: 7096434 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.7061. Min Act: -0.1700
Data Index: 4450851 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.6748. Min Act: -0.1700
Data Index: 3729130 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.6748. Min Act: -0.1700
Data Index: 4340120 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.6748. Min Act: -0.1700
Data Index: 8225289 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.6748. Min Act: -0.1700
Data Index: 7231383 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.6748. Min Act: -0.1700
Data Index: 8003022 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.6436. Min Act: -0.1700
Data Index: 1178845 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.6748. Min Act: -0.1700
Data Index: 6093541 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.6123. Min Act: -0.1700
Data Index: 798617 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19