Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5111 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3870. Min Range: -10.3870
Max Act: 10.3870. Min Act: -0.1700
Data Index: 813168 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3870. Min Range: -10.3870
Max Act: 10.1995. Min Act: -0.1700
Data Index: 7948525 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3870. Min Range: -10.3870
Max Act: 10.1995. Min Act: -0.1700
Data Index: 5029730 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3870. Min Range: -10.3870
Max Act: 10.0745. Min Act: -0.1700
Data Index: 6334158 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3870. Min Range: -10.3870
Max Act: 10.0745. Min Act: -0.1700
Data Index: 6899303 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3870. Min Range: -10.3870
Max Act: 10.0745. Min Act: -0.1700
Data Index: 5828832 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3870. Min Range: -10.3870
Max Act: 10.0745. Min Act: -0.1700
Data Index: 7561352 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3870. Min Range: -10.3870
Max Act: 10.0120. Min Act: -0.1700
Data Index: 1197437 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3870. Min Range: -10.3870
Max Act: 10.0120. Min Act: -0.1700
Data Index: 1804309 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3870. Min Range: -10.3870
Max Act: 9.9495. Min Act: -0.1700
Data Index: 6657324 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3870. Min Range: -10.3870
Max Act: 10.0120. Min Act: -0.1700
Data Index: 4088639 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3870. Min Range: -10.3870
Max Act: 9.9495. Min Act: -0.1700
Data Index: 3499514 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3870. Min Range: -10.3870
Max Act: 9.9495. Min Act: -0.1700
Data Index: 5969457 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3870. Min Range: -10.3870
Max Act: 9.9495. Min Act: -0.1700
Data Index: 3698757 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3870. Min Range: -10.3870
Max Act: 9.9495. Min Act: -0.1700
Data Index: 8793448 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3870. Min Range: -10.3870
Max Act: 9.9495. Min Act: -0.1700
Data Index: 6751196 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3870. Min Range: -10.3870
Max Act: 9.8870. Min Act: -0.1700
Data Index: 5683411 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3870. Min Range: -10.3870
Max Act: 9.8245. Min Act: -0.1700
Data Index: 1975906 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3870. Min Range: -10.3870
Max Act: 9.8245. Min Act: -0.1700
Data Index: 1808933 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3870. Min Range: -10.3870
Max Act: 9.8245. Min Act: -0.1700
Data Index: 7240080 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19