Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.9539. Min Act: -0.1700
Data Index: 3535649 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.9539. Min Act: -0.1700
Data Index: 8504030 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.8601. Min Act: -0.1700
Data Index: 1613044 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.6726. Min Act: -0.1700
Data Index: 1245048 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.6414. Min Act: -0.1700
Data Index: 3077333 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.6726. Min Act: -0.1700
Data Index: 5317846 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.6414. Min Act: -0.1700
Data Index: 4465699 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.5789. Min Act: -0.1700
Data Index: 78588 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.6101. Min Act: -0.1700
Data Index: 2002888 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.5476. Min Act: -0.1700
Data Index: 8732111 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.5164. Min Act: -0.1700
Data Index: 1513551 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.4851. Min Act: -0.1700
Data Index: 1006629 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.4539. Min Act: -0.1700
Data Index: 5139075 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.4539. Min Act: -0.1700
Data Index: 8441403 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.4226. Min Act: -0.1700
Data Index: 5401588 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.4226. Min Act: -0.1700
Data Index: 6248743 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.4226. Min Act: -0.1700
Data Index: 3722192 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.4226. Min Act: -0.1700
Data Index: 2904831 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.3914. Min Act: -0.1700
Data Index: 6855615 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9539. Min Range: -5.9539
Max Act: 5.3914. Min Act: -0.1700
Data Index: 1759955 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19