Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2132. Min Range: -6.2132
Max Act: 6.2132. Min Act: -0.1700
Data Index: 169832 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2132. Min Range: -6.2132
Max Act: 6.0882. Min Act: -0.1700
Data Index: 2918882 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2132. Min Range: -6.2132
Max Act: 6.0882. Min Act: -0.1700
Data Index: 1697244 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2132. Min Range: -6.2132
Max Act: 6.0257. Min Act: -0.1700
Data Index: 6571722 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2132. Min Range: -6.2132
Max Act: 6.0257. Min Act: -0.1700
Data Index: 685888 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2132. Min Range: -6.2132
Max Act: 6.0569. Min Act: -0.1700
Data Index: 6566389 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.9632. Min Act: -0.1700
Data Index: 4927616 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.9319. Min Act: -0.1700
Data Index: 1084868 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.9007. Min Act: -0.1700
Data Index: 4704700 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8694. Min Act: -0.1700
Data Index: 644389 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8694. Min Act: -0.1700
Data Index: 1625487 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8694. Min Act: -0.1700
Data Index: 3107891 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8382. Min Act: -0.1700
Data Index: 4152841 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8382. Min Act: -0.1700
Data Index: 3445562 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8382. Min Act: -0.1700
Data Index: 355677 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8069. Min Act: -0.1700
Data Index: 6141514 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8069. Min Act: -0.1700
Data Index: 7914179 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8069. Min Act: -0.1700
Data Index: 2322032 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8069. Min Act: -0.1700
Data Index: 3672131 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8069. Min Act: -0.1700
Data Index: 7819242 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19