Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 793 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.5122. Min Act: -0.1700
Data Index: 133931 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.4497. Min Act: -0.1700
Data Index: 4175200 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.3559. Min Act: -0.1700
Data Index: 413699 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.3559. Min Act: -0.1700
Data Index: 840183 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.3247. Min Act: -0.1700
Data Index: 1702298 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.2934. Min Act: -0.1700
Data Index: 2907306 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.2934. Min Act: -0.1700
Data Index: 1697942 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.2934. Min Act: -0.1700
Data Index: 6622084 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.2934. Min Act: -0.1700
Data Index: 6932475 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.2622. Min Act: -0.1700
Data Index: 945547 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.2622. Min Act: -0.1700
Data Index: 2325530 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.2309. Min Act: -0.1700
Data Index: 3014956 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1997. Min Act: -0.1700
Data Index: 2581289 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1997. Min Act: -0.1700
Data Index: 4437353 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1684. Min Act: -0.1700
Data Index: 2858930 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1997. Min Act: -0.1700
Data Index: 1795259 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1684. Min Act: -0.1700
Data Index: 6304480 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1684. Min Act: -0.1700
Data Index: 3968287 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1059. Min Act: -0.1700
Data Index: 7182076 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5122. Min Range: -6.5122
Max Act: 6.1372. Min Act: -0.1700
Data Index: 6313950 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19