Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5424 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0013. Min Range: -6.0013
Max Act: 6.0013. Min Act: -0.1700
Data Index: 7616629 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.8763. Min Act: -0.1700
Data Index: 397994 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.6888. Min Act: -0.1700
Data Index: 4643715 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.6263. Min Act: -0.1700
Data Index: 7879338 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.6263. Min Act: -0.1700
Data Index: 7407319 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.5950. Min Act: -0.1700
Data Index: 6363367 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.5013. Min Act: -0.1700
Data Index: 1704231 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.4700. Min Act: -0.1700
Data Index: 260510 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.4700. Min Act: -0.1700
Data Index: 6711365 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.4700. Min Act: -0.1700
Data Index: 498793 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.4388. Min Act: -0.1700
Data Index: 217446 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.4388. Min Act: -0.1700
Data Index: 8690635 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.4388. Min Act: -0.1700
Data Index: 4161863 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.4075. Min Act: -0.1700
Data Index: 8785404 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.4075. Min Act: -0.1700
Data Index: 2964083 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.4075. Min Act: -0.1700
Data Index: 2616370 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.3763. Min Act: -0.1700
Data Index: 2247089 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.3763. Min Act: -0.1700
Data Index: 5004224 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.3138. Min Act: -0.1700
Data Index: 2703585 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0013. Min Range: -6.0013
Max Act: 5.3138. Min Act: -0.1700
Data Index: 6627992 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19