Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4221 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5926. Min Range: -7.5926
Max Act: 7.5926. Min Act: -0.1700
Data Index: 271757 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.8426. Min Act: -0.1700
Data Index: 1526725 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.6551. Min Act: -0.1700
Data Index: 2803296 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.6551. Min Act: -0.1700
Data Index: 3144198 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.6551. Min Act: -0.1700
Data Index: 5742304 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.6239. Min Act: -0.1700
Data Index: 5129685 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.6239. Min Act: -0.1700
Data Index: 4478288 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.6239. Min Act: -0.1700
Data Index: 2111301 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.5926. Min Act: -0.1700
Data Index: 823949 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.5614. Min Act: -0.1700
Data Index: 5847126 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.5614. Min Act: -0.1700
Data Index: 70276 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.4989. Min Act: -0.1700
Data Index: 6980885 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.4989. Min Act: -0.1700
Data Index: 7113448 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.4676. Min Act: -0.1700
Data Index: 7482060 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.4364. Min Act: -0.1700
Data Index: 7404605 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.3739. Min Act: -0.1700
Data Index: 5077316 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.4364. Min Act: -0.1700
Data Index: 8261776 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.3739. Min Act: -0.1700
Data Index: 7614733 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.4051. Min Act: -0.1700
Data Index: 3809808 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5926. Min Range: -7.5926
Max Act: 6.3739. Min Act: -0.1700
Data Index: 6046036 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19