Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3379 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.6390. Min Act: -0.1700
Data Index: 1408639 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.3577. Min Act: -0.1700
Data Index: 162908 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.3265. Min Act: -0.1700
Data Index: 4049751 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.2640. Min Act: -0.1700
Data Index: 6099914 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.1702. Min Act: -0.1700
Data Index: 8594271 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.1702. Min Act: -0.1700
Data Index: 1408638 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.1702. Min Act: -0.1700
Data Index: 3852074 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.1390. Min Act: -0.1700
Data Index: 1303835 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.1390. Min Act: -0.1700
Data Index: 4515619 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.1390. Min Act: -0.1700
Data Index: 8594270 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.1077. Min Act: -0.1700
Data Index: 2846678 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.1077. Min Act: -0.1700
Data Index: 517078 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.0765. Min Act: -0.1700
Data Index: 2272237 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.0765. Min Act: -0.1700
Data Index: 8744737 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.0452. Min Act: -0.1700
Data Index: 7900948 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.0452. Min Act: -0.1700
Data Index: 4345868 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.0140. Min Act: -0.1700
Data Index: 7841791 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.0140. Min Act: -0.1700
Data Index: 3751353 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6390. Min Range: -6.6390
Max Act: 6.0140. Min Act: -0.1700
Data Index: 162925 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6390. Min Range: -6.6390
Max Act: 5.9827. Min Act: -0.1700
Data Index: 1408630 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19