Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.7105. Min Act: -0.1700
Data Index: 5638612 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.5230. Min Act: -0.1700
Data Index: 580030 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.5230. Min Act: -0.1700
Data Index: 534268 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.4917. Min Act: -0.1700
Data Index: 7392750 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.4605. Min Act: -0.1700
Data Index: 1639588 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.4605. Min Act: -0.1700
Data Index: 8679130 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.4292. Min Act: -0.1700
Data Index: 7478513 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.4917. Min Act: -0.1700
Data Index: 7406952 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.4917. Min Act: -0.1700
Data Index: 1052710 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.4605. Min Act: -0.1700
Data Index: 643356 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.4605. Min Act: -0.1700
Data Index: 86520 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.3980. Min Act: -0.1700
Data Index: 106466 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.4605. Min Act: -0.1700
Data Index: 3074047 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.3667. Min Act: -0.1700
Data Index: 5302032 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.3980. Min Act: -0.1700
Data Index: 3161862 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.3980. Min Act: -0.1700
Data Index: 6949530 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.3667. Min Act: -0.1700
Data Index: 248939 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.3980. Min Act: -0.1700
Data Index: 598218 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.4292. Min Act: -0.1700
Data Index: 7472169 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7105. Min Range: -6.7105
Max Act: 6.3980. Min Act: -0.1700
Data Index: 8411356 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19