Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2925 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8807. Min Range: -9.8807
Max Act: 9.8807. Min Act: -0.1700
Data Index: 6167717 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8807. Min Range: -9.8807
Max Act: 9.5057. Min Act: -0.1700
Data Index: 6028654 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8807. Min Range: -9.8807
Max Act: 9.3807. Min Act: -0.1700
Data Index: 1788770 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8807. Min Range: -9.8807
Max Act: 9.1932. Min Act: -0.1700
Data Index: 3717596 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8807. Min Range: -9.8807
Max Act: 9.1932. Min Act: -0.1700
Data Index: 8200585 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8807. Min Range: -9.8807
Max Act: 9.0057. Min Act: -0.1700
Data Index: 2847241 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.9432. Min Act: -0.1700
Data Index: 6460850 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.9432. Min Act: -0.1700
Data Index: 2572995 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.9432. Min Act: -0.1700
Data Index: 7293328 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.8807. Min Act: -0.1700
Data Index: 2543033 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.9432. Min Act: -0.1700
Data Index: 101438 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.8807. Min Act: -0.1700
Data Index: 3122428 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.8807. Min Act: -0.1700
Data Index: 8729830 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.8182. Min Act: -0.1700
Data Index: 906451 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.7557. Min Act: -0.1700
Data Index: 2353443 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.7557. Min Act: -0.1700
Data Index: 6010063 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.7557. Min Act: -0.1700
Data Index: 3664692 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.6307. Min Act: -0.1700
Data Index: 1646877 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.6307. Min Act: -0.1700
Data Index: 5827310 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8807. Min Range: -9.8807
Max Act: 8.6307. Min Act: -0.1700
Data Index: 2494271 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19