Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6352 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.7267. Min Act: -0.1700
Data Index: 5063587 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.5392. Min Act: -0.1700
Data Index: 861028 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.3829. Min Act: -0.1700
Data Index: 8274120 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.2892. Min Act: -0.1700
Data Index: 6916116 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.2579. Min Act: -0.1700
Data Index: 8453943 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.1642. Min Act: -0.1700
Data Index: 2747664 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.1642. Min Act: -0.1700
Data Index: 1505904 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.1642. Min Act: -0.1700
Data Index: 8049963 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.1017. Min Act: -0.1700
Data Index: 3797473 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.0704. Min Act: -0.1700
Data Index: 4029743 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.0704. Min Act: -0.1700
Data Index: 4644656 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.0704. Min Act: -0.1700
Data Index: 2255792 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.0704. Min Act: -0.1700
Data Index: 3538621 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.0704. Min Act: -0.1700
Data Index: 5913380 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.0392. Min Act: -0.1700
Data Index: 6905060 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.0392. Min Act: -0.1700
Data Index: 116631 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.0392. Min Act: -0.1700
Data Index: 2490786 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7267. Min Range: -7.7267
Max Act: 7.0392. Min Act: -0.1700
Data Index: 6382372 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7267. Min Range: -7.7267
Max Act: 6.9767. Min Act: -0.1700
Data Index: 18425 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7267. Min Range: -7.7267
Max Act: 6.9767. Min Act: -0.1700
Data Index: 5965689 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19