Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6046 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.9309. Min Act: -0.1700
Data Index: 5937978 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.8997. Min Act: -0.1700
Data Index: 5249504 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.8059. Min Act: -0.1700
Data Index: 2731843 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.7747. Min Act: -0.1700
Data Index: 4506094 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.7434. Min Act: -0.1700
Data Index: 5609659 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.7122. Min Act: -0.1700
Data Index: 1226235 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.6809. Min Act: -0.1700
Data Index: 968124 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.6497. Min Act: -0.1700
Data Index: 4713009 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.6809. Min Act: -0.1700
Data Index: 2304797 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.6184. Min Act: -0.1700
Data Index: 6215313 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.6184. Min Act: -0.1700
Data Index: 6736001 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.6184. Min Act: -0.1700
Data Index: 622829 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.6184. Min Act: -0.1700
Data Index: 849779 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.6184. Min Act: -0.1700
Data Index: 4161080 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.5872. Min Act: -0.1700
Data Index: 5095923 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.6184. Min Act: -0.1700
Data Index: 1995909 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.6184. Min Act: -0.1700
Data Index: 1413653 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.6184. Min Act: -0.1700
Data Index: 7476120 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.6184. Min Act: -0.1700
Data Index: 5320881 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9309. Min Range: -5.9309
Max Act: 5.6184. Min Act: -0.1700
Data Index: 5445293 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19