Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5198 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.4787. Min Act: -0.1700
Data Index: 8223924 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.3850. Min Act: -0.1700
Data Index: 3919195 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.3537. Min Act: -0.1700
Data Index: 4207457 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.3537. Min Act: -0.1700
Data Index: 2977342 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.3225. Min Act: -0.1700
Data Index: 2468181 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.3225. Min Act: -0.1700
Data Index: 3860181 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.2912. Min Act: -0.1700
Data Index: 3779935 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.2912. Min Act: -0.1700
Data Index: 6402725 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.2287. Min Act: -0.1700
Data Index: 2122217 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.1975. Min Act: -0.1700
Data Index: 345865 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.1975. Min Act: -0.1700
Data Index: 3184710 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.1975. Min Act: -0.1700
Data Index: 3779931 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.1975. Min Act: -0.1700
Data Index: 2048979 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.1975. Min Act: -0.1700
Data Index: 1368977 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.1975. Min Act: -0.1700
Data Index: 3028700 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.1662. Min Act: -0.1700
Data Index: 5694662 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.1350. Min Act: -0.1700
Data Index: 7716970 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.1350. Min Act: -0.1700
Data Index: 1314727 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.1350. Min Act: -0.1700
Data Index: 4300719 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4787. Min Range: -6.4787
Max Act: 6.1037. Min Act: -0.1700
Data Index: 4300722 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19