Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2194 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.5404. Min Act: -0.1700
Data Index: 4402349 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.5092. Min Act: -0.1700
Data Index: 591055 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.5092. Min Act: -0.1700
Data Index: 243678 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.4467. Min Act: -0.1700
Data Index: 5169935 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.3842. Min Act: -0.1700
Data Index: 8728867 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.3529. Min Act: -0.1700
Data Index: 2884653 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.3217. Min Act: -0.1700
Data Index: 7182766 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.2904. Min Act: -0.1700
Data Index: 1644535 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.2279. Min Act: -0.1700
Data Index: 7383898 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.2279. Min Act: -0.1700
Data Index: 6426549 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.1342. Min Act: -0.1700
Data Index: 3344329 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.1654. Min Act: -0.1700
Data Index: 6125989 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.1654. Min Act: -0.1700
Data Index: 8490902 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.1342. Min Act: -0.1700
Data Index: 3827930 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.1342. Min Act: -0.1700
Data Index: 1758111 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.1029. Min Act: -0.1700
Data Index: 8074839 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.0717. Min Act: -0.1700
Data Index: 494074 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.1029. Min Act: -0.1700
Data Index: 4897763 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.1029. Min Act: -0.1700
Data Index: 2746892 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5404. Min Range: -6.5404
Max Act: 6.0717. Min Act: -0.1700
Data Index: 4286102 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19