Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.3171. Min Act: -0.1700
Data Index: 654442 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.2859. Min Act: -0.1700
Data Index: 1770776 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.2859. Min Act: -0.1700
Data Index: 6557233 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.2859. Min Act: -0.1700
Data Index: 3174953 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.1921. Min Act: -0.1700
Data Index: 1924926 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.1609. Min Act: -0.1700
Data Index: 2769401 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.0984. Min Act: -0.1700
Data Index: 892875 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.0984. Min Act: -0.1700
Data Index: 2102906 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.0984. Min Act: -0.1700
Data Index: 6976567 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.0671. Min Act: -0.1700
Data Index: 3917706 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.0671. Min Act: -0.1700
Data Index: 8223014 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.0359. Min Act: -0.1700
Data Index: 6229752 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.0359. Min Act: -0.1700
Data Index: 3520128 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.0359. Min Act: -0.1700
Data Index: 3374677 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.0046. Min Act: -0.1700
Data Index: 5540305 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.0046. Min Act: -0.1700
Data Index: 7884158 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.0046. Min Act: -0.1700
Data Index: 149126 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.0046. Min Act: -0.1700
Data Index: 1633388 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3171. Min Range: -6.3171
Max Act: 6.0046. Min Act: -0.1700
Data Index: 5788488 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3171. Min Range: -6.3171
Max Act: 5.9734. Min Act: -0.1700
Data Index: 3858780 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19