Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3049 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2721. Min Range: -8.2721
Max Act: 8.2721. Min Act: -0.1700
Data Index: 826290 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2721. Min Range: -8.2721
Max Act: 8.2096. Min Act: -0.1700
Data Index: 2991601 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2721. Min Range: -8.2721
Max Act: 8.0221. Min Act: -0.1700
Data Index: 3579620 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.8346. Min Act: -0.1700
Data Index: 7363282 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.8971. Min Act: -0.1700
Data Index: 3720790 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.8971. Min Act: -0.1700
Data Index: 1181608 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.8971. Min Act: -0.1700
Data Index: 4784645 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.8346. Min Act: -0.1700
Data Index: 8481882 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.8346. Min Act: -0.1700
Data Index: 5331840 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.8346. Min Act: -0.1700
Data Index: 560833 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.8346. Min Act: -0.1700
Data Index: 6074268 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.7721. Min Act: -0.1700
Data Index: 84959 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.7721. Min Act: -0.1700
Data Index: 3155522 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.7721. Min Act: -0.1700
Data Index: 2895338 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.7721. Min Act: -0.1700
Data Index: 1510036 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.7721. Min Act: -0.1700
Data Index: 2822066 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.7096. Min Act: -0.1700
Data Index: 4039798 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.7096. Min Act: -0.1700
Data Index: 804987 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.7096. Min Act: -0.1700
Data Index: 5796697 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2721. Min Range: -8.2721
Max Act: 7.7096. Min Act: -0.1700
Data Index: 7794525 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19