Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5177 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.8551. Min Act: -0.1700
Data Index: 4746929 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.8239. Min Act: -0.1700
Data Index: 5472538 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.6364. Min Act: -0.1700
Data Index: 7106689 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.5114. Min Act: -0.1700
Data Index: 6981095 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.4489. Min Act: -0.1700
Data Index: 6316556 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.4176. Min Act: -0.1700
Data Index: 7243575 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.3864. Min Act: -0.1700
Data Index: 5277637 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.3239. Min Act: -0.1700
Data Index: 556635 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.2926. Min Act: -0.1700
Data Index: 4431866 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.1989. Min Act: -0.1700
Data Index: 2887157 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.1676. Min Act: -0.1700
Data Index: 1505637 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.1051. Min Act: -0.1700
Data Index: 8128475 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.1051. Min Act: -0.1700
Data Index: 7683242 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.0739. Min Act: -0.1700
Data Index: 543198 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.0426. Min Act: -0.1700
Data Index: 1973483 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.0114. Min Act: -0.1700
Data Index: 1839616 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8551. Min Range: -6.8551
Max Act: 5.9801. Min Act: -0.1700
Data Index: 4979447 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8551. Min Range: -6.8551
Max Act: 6.0114. Min Act: -0.1700
Data Index: 8760577 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8551. Min Range: -6.8551
Max Act: 5.9801. Min Act: -0.1700
Data Index: 1141838 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8551. Min Range: -6.8551
Max Act: 5.9801. Min Act: -0.1700
Data Index: 715658 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19