Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2401 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3808. Min Range: -6.3808
Max Act: 6.3808. Min Act: -0.1700
Data Index: 4768849 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3808. Min Range: -6.3808
Max Act: 6.1621. Min Act: -0.1700
Data Index: 2255551 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3808. Min Range: -6.3808
Max Act: 6.1308. Min Act: -0.1700
Data Index: 4305945 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3808. Min Range: -6.3808
Max Act: 6.1621. Min Act: -0.1700
Data Index: 4136071 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3808. Min Range: -6.3808
Max Act: 6.0683. Min Act: -0.1700
Data Index: 8056853 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.9433. Min Act: -0.1700
Data Index: 3025441 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.9121. Min Act: -0.1700
Data Index: 6438273 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.8808. Min Act: -0.1700
Data Index: 2843406 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.8496. Min Act: -0.1700
Data Index: 2577910 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.8496. Min Act: -0.1700
Data Index: 334007 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.8496. Min Act: -0.1700
Data Index: 455882 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.8496. Min Act: -0.1700
Data Index: 6647885 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.8183. Min Act: -0.1700
Data Index: 2534737 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.8183. Min Act: -0.1700
Data Index: 6814795 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.8183. Min Act: -0.1700
Data Index: 4066589 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.8183. Min Act: -0.1700
Data Index: 4218667 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.7871. Min Act: -0.1700
Data Index: 3668645 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.7558. Min Act: -0.1700
Data Index: 7982977 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.7558. Min Act: -0.1700
Data Index: 789427 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3808. Min Range: -6.3808
Max Act: 5.7558. Min Act: -0.1700
Data Index: 6328547 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19