Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3710 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.8018. Min Act: -0.1700
Data Index: 76726 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.6768. Min Act: -0.1700
Data Index: 8495695 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.6455. Min Act: -0.1700
Data Index: 6307650 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.6455. Min Act: -0.1700
Data Index: 895465 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.5830. Min Act: -0.1700
Data Index: 6103431 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.5830. Min Act: -0.1700
Data Index: 5273697 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.5205. Min Act: -0.1700
Data Index: 5260709 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.4893. Min Act: -0.1700
Data Index: 3827845 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.4268. Min Act: -0.1700
Data Index: 7681693 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.4580. Min Act: -0.1700
Data Index: 6103426 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.4268. Min Act: -0.1700
Data Index: 902018 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.3955. Min Act: -0.1700
Data Index: 6568239 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.3955. Min Act: -0.1700
Data Index: 1530099 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.3955. Min Act: -0.1700
Data Index: 6197611 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.3955. Min Act: -0.1700
Data Index: 7021370 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.3643. Min Act: -0.1700
Data Index: 97110 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.3643. Min Act: -0.1700
Data Index: 5720648 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.3330. Min Act: -0.1700
Data Index: 644752 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.3643. Min Act: -0.1700
Data Index: 3861632 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8018. Min Range: -5.8018
Max Act: 5.3643. Min Act: -0.1700
Data Index: 6898476 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19