Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 355 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.8392. Min Act: -0.1700
Data Index: 2141480 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.7767. Min Act: -0.1700
Data Index: 6112625 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.8080. Min Act: -0.1700
Data Index: 5893246 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.7142. Min Act: -0.1700
Data Index: 2996682 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.6830. Min Act: -0.1700
Data Index: 8244584 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.6205. Min Act: -0.1700
Data Index: 6824676 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.6205. Min Act: -0.1700
Data Index: 5633264 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.6205. Min Act: -0.1700
Data Index: 7676462 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.5580. Min Act: -0.1700
Data Index: 4891914 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.5267. Min Act: -0.1700
Data Index: 8079011 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.5267. Min Act: -0.1700
Data Index: 3384089 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.5267. Min Act: -0.1700
Data Index: 1189943 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.5267. Min Act: -0.1700
Data Index: 4655065 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.4955. Min Act: -0.1700
Data Index: 7145460 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.4955. Min Act: -0.1700
Data Index: 5736809 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.4955. Min Act: -0.1700
Data Index: 8066711 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.5267. Min Act: -0.1700
Data Index: 8650707 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.4642. Min Act: -0.1700
Data Index: 7417971 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.4642. Min Act: -0.1700
Data Index: 851644 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8392. Min Range: -5.8392
Max Act: 5.4955. Min Act: -0.1700
Data Index: 7819929 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19