Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7168. Min Range: -8.7168
Max Act: 8.7168. Min Act: -0.1700
Data Index: 5220464 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7168. Min Range: -8.7168
Max Act: 8.3418. Min Act: -0.1700
Data Index: 1805516 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7168. Min Range: -8.7168
Max Act: 8.2793. Min Act: -0.1700
Data Index: 5918295 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7168. Min Range: -8.7168
Max Act: 8.2168. Min Act: -0.1700
Data Index: 4502632 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7168. Min Range: -8.7168
Max Act: 8.1543. Min Act: -0.1700
Data Index: 7711973 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7168. Min Range: -8.7168
Max Act: 8.1543. Min Act: -0.1700
Data Index: 2557833 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7168. Min Range: -8.7168
Max Act: 8.1543. Min Act: -0.1700
Data Index: 7833859 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7168. Min Range: -8.7168
Max Act: 8.1231. Min Act: -0.1700
Data Index: 7891687 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7168. Min Range: -8.7168
Max Act: 8.0606. Min Act: -0.1700
Data Index: 4945311 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7168. Min Range: -8.7168
Max Act: 7.9981. Min Act: -0.1700
Data Index: 7872458 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7168. Min Range: -8.7168
Max Act: 7.9668. Min Act: -0.1700
Data Index: 1210053 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7168. Min Range: -8.7168
Max Act: 7.9668. Min Act: -0.1700
Data Index: 8069570 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7168. Min Range: -8.7168
Max Act: 7.9356. Min Act: -0.1700
Data Index: 4964340 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7168. Min Range: -8.7168
Max Act: 7.9043. Min Act: -0.1700
Data Index: 4399408 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7168. Min Range: -8.7168
Max Act: 7.9043. Min Act: -0.1700
Data Index: 6475117 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7168. Min Range: -8.7168
Max Act: 7.9043. Min Act: -0.1700
Data Index: 219086 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7168. Min Range: -8.7168
Max Act: 7.8731. Min Act: -0.1700
Data Index: 5621002 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7168. Min Range: -8.7168
Max Act: 7.8418. Min Act: -0.1700
Data Index: 3782887 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7168. Min Range: -8.7168
Max Act: 7.8418. Min Act: -0.1700
Data Index: 7979959 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7168. Min Range: -8.7168
Max Act: 7.8106. Min Act: -0.1700
Data Index: 7376429 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19