Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6072 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.9896. Min Act: -0.1700
Data Index: 4473405 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.9583. Min Act: -0.1700
Data Index: 252166 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.8958. Min Act: -0.1700
Data Index: 5810847 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.8333. Min Act: -0.1700
Data Index: 1606282 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.8333. Min Act: -0.1700
Data Index: 2518676 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.8333. Min Act: -0.1700
Data Index: 1917423 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.8021. Min Act: -0.1700
Data Index: 3008056 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.8021. Min Act: -0.1700
Data Index: 2696554 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.7708. Min Act: -0.1700
Data Index: 5722597 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.7708. Min Act: -0.1700
Data Index: 8525335 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.7708. Min Act: -0.1700
Data Index: 4743510 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.7396. Min Act: -0.1700
Data Index: 8307576 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.7396. Min Act: -0.1700
Data Index: 1380733 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.7396. Min Act: -0.1700
Data Index: 7315950 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.7396. Min Act: -0.1700
Data Index: 2554503 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.7083. Min Act: -0.1700
Data Index: 5382295 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.6771. Min Act: -0.1700
Data Index: 4288890 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.6771. Min Act: -0.1700
Data Index: 6420338 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.6771. Min Act: -0.1700
Data Index: 179876 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9896. Min Range: -5.9896
Max Act: 5.7083. Min Act: -0.1700
Data Index: 2571586 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19