Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5215 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0294. Min Range: -7.0294
Max Act: 7.0294. Min Act: -0.1700
Data Index: 7155931 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.7794. Min Act: -0.1700
Data Index: 2423181 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.7481. Min Act: -0.1700
Data Index: 8274981 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.7169. Min Act: -0.1700
Data Index: 6729903 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.7169. Min Act: -0.1700
Data Index: 7944556 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.7169. Min Act: -0.1700
Data Index: 3782641 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.5919. Min Act: -0.1700
Data Index: 4671626 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.6231. Min Act: -0.1700
Data Index: 999052 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.5606. Min Act: -0.1700
Data Index: 1422979 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.5606. Min Act: -0.1700
Data Index: 3760177 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.5606. Min Act: -0.1700
Data Index: 6747383 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.5294. Min Act: -0.1700
Data Index: 4125214 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.5294. Min Act: -0.1700
Data Index: 8164929 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.4981. Min Act: -0.1700
Data Index: 4594990 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.4669. Min Act: -0.1700
Data Index: 7681797 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.4981. Min Act: -0.1700
Data Index: 7127690 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.4981. Min Act: -0.1700
Data Index: 1778144 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.4981. Min Act: -0.1700
Data Index: 4217279 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.4356. Min Act: -0.1700
Data Index: 8328232 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0294. Min Range: -7.0294
Max Act: 6.4669. Min Act: -0.1700
Data Index: 1643253 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19