Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2863 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.7264. Min Act: -0.1700
Data Index: 8199192 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.6952. Min Act: -0.1700
Data Index: 3649369 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.6952. Min Act: -0.1700
Data Index: 2549505 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.4764. Min Act: -0.1700
Data Index: 2448945 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.4764. Min Act: -0.1700
Data Index: 6309010 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.4452. Min Act: -0.1700
Data Index: 2448940 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.4764. Min Act: -0.1700
Data Index: 3112484 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.4764. Min Act: -0.1700
Data Index: 5187723 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.4139. Min Act: -0.1700
Data Index: 76248 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.4452. Min Act: -0.1700
Data Index: 7397737 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.3827. Min Act: -0.1700
Data Index: 2430290 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.3827. Min Act: -0.1700
Data Index: 2722144 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.3827. Min Act: -0.1700
Data Index: 6777115 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.4139. Min Act: -0.1700
Data Index: 1876790 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.3514. Min Act: -0.1700
Data Index: 2211645 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.3827. Min Act: -0.1700
Data Index: 3210142 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.3514. Min Act: -0.1700
Data Index: 5447507 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.3514. Min Act: -0.1700
Data Index: 1481252 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.3202. Min Act: -0.1700
Data Index: 1493002 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7264. Min Range: -5.7264
Max Act: 5.2889. Min Act: -0.1700
Data Index: 732765 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19