Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3053 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3430. Min Range: -6.3430
Max Act: 6.3430. Min Act: -0.1700
Data Index: 7837195 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3430. Min Range: -6.3430
Max Act: 6.1555. Min Act: -0.1700
Data Index: 3755760 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.8742. Min Act: -0.1700
Data Index: 7306400 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.8117. Min Act: -0.1700
Data Index: 2593579 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.7492. Min Act: -0.1700
Data Index: 7975638 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.7805. Min Act: -0.1700
Data Index: 3561642 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.7180. Min Act: -0.1700
Data Index: 4251257 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.6867. Min Act: -0.1700
Data Index: 2966022 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.7180. Min Act: -0.1700
Data Index: 7735776 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.6867. Min Act: -0.1700
Data Index: 3547437 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.6555. Min Act: -0.1700
Data Index: 3722151 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.6867. Min Act: -0.1700
Data Index: 8544188 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.6555. Min Act: -0.1700
Data Index: 8104305 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.6555. Min Act: -0.1700
Data Index: 6875194 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.6242. Min Act: -0.1700
Data Index: 7469506 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.6242. Min Act: -0.1700
Data Index: 1375756 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.6555. Min Act: -0.1700
Data Index: 3952639 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.6242. Min Act: -0.1700
Data Index: 7776120 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.6242. Min Act: -0.1700
Data Index: 4069493 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3430. Min Range: -6.3430
Max Act: 5.5930. Min Act: -0.1700
Data Index: 8127718 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19