Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4322 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.8988. Min Act: -0.1700
Data Index: 4014928 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.8363. Min Act: -0.1700
Data Index: 1026803 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.8051. Min Act: -0.1700
Data Index: 4014931 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.7426. Min Act: -0.1700
Data Index: 3356996 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.6176. Min Act: -0.1700
Data Index: 2149571 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.5863. Min Act: -0.1699
Data Index: 2220827 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.5551. Min Act: -0.1700
Data Index: 5480075 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.4926. Min Act: -0.1700
Data Index: 7869895 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.4301. Min Act: -0.1700
Data Index: 8026541 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.3988. Min Act: -0.1700
Data Index: 1229713 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.3988. Min Act: -0.1700
Data Index: 7261307 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.3676. Min Act: -0.1696
Data Index: 2144216 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.3988. Min Act: -0.1700
Data Index: 3356998 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.3676. Min Act: -0.1700
Data Index: 8148112 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.3051. Min Act: -0.1700
Data Index: 4468821 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.2738. Min Act: -0.1699
Data Index: 5521378 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.2738. Min Act: -0.1700
Data Index: 6119104 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.2426. Min Act: -0.1699
Data Index: 5056158 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.2426. Min Act: -0.1700
Data Index: 4299861 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8988. Min Range: -5.8988
Max Act: 5.2426. Min Act: -0.1700
Data Index: 5442280 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19