Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 669 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.9045. Min Act: -0.1700
Data Index: 1138196 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.3420. Min Act: -0.1700
Data Index: 35140 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.3107. Min Act: -0.1700
Data Index: 5203911 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.2795. Min Act: -0.1700
Data Index: 8144435 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.2795. Min Act: -0.1700
Data Index: 4821355 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.2482. Min Act: -0.1700
Data Index: 5145456 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.1857. Min Act: -0.1700
Data Index: 5875604 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.1545. Min Act: -0.1700
Data Index: 2024202 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.1545. Min Act: -0.1700
Data Index: 1587337 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.1232. Min Act: -0.1700
Data Index: 7940552 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.1232. Min Act: -0.1700
Data Index: 2715547 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.1232. Min Act: -0.1700
Data Index: 8166974 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.0920. Min Act: -0.1700
Data Index: 1710389 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.0920. Min Act: -0.1700
Data Index: 2696657 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.0607. Min Act: -0.1700
Data Index: 5179935 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.0607. Min Act: -0.1700
Data Index: 6909576 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.0295. Min Act: -0.1700
Data Index: 5880923 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.0295. Min Act: -0.1700
Data Index: 3336047 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.0295. Min Act: -0.1700
Data Index: 8354111 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9045. Min Range: -6.9045
Max Act: 6.0295. Min Act: -0.1700
Data Index: 3020178 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19