Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5093 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2870. Min Range: -7.2870
Max Act: 7.2870. Min Act: -0.1700
Data Index: 6958740 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2870. Min Range: -7.2870
Max Act: 7.1308. Min Act: -0.1700
Data Index: 8012675 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2870. Min Range: -7.2870
Max Act: 7.0370. Min Act: -0.1700
Data Index: 7812119 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.9120. Min Act: -0.1700
Data Index: 41073 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.8495. Min Act: -0.1700
Data Index: 191596 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.8183. Min Act: -0.1700
Data Index: 4136343 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.7870. Min Act: -0.1700
Data Index: 566379 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.7558. Min Act: -0.1700
Data Index: 470417 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.7558. Min Act: -0.1700
Data Index: 7318028 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.7245. Min Act: -0.1700
Data Index: 6907001 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.7245. Min Act: -0.1700
Data Index: 7718289 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.6933. Min Act: -0.1700
Data Index: 7914609 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.6933. Min Act: -0.1700
Data Index: 1858008 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.6933. Min Act: -0.1700
Data Index: 7903839 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.6620. Min Act: -0.1700
Data Index: 105563 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.6933. Min Act: -0.1700
Data Index: 5531858 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.6620. Min Act: -0.1700
Data Index: 4377316 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.6620. Min Act: -0.1700
Data Index: 7794782 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.6620. Min Act: -0.1700
Data Index: 2659186 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2870. Min Range: -7.2870
Max Act: 6.6620. Min Act: -0.1700
Data Index: 5971131 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19