Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.6292. Min Act: -0.1700
Data Index: 109173 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.5355. Min Act: -0.1700
Data Index: 342231 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.3792. Min Act: -0.1700
Data Index: 2552795 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.3792. Min Act: -0.1700
Data Index: 8346108 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.3480. Min Act: -0.1700
Data Index: 1884434 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.3480. Min Act: -0.1700
Data Index: 7546560 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.3792. Min Act: -0.1700
Data Index: 7546566 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.3167. Min Act: -0.1700
Data Index: 1676830 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.3480. Min Act: -0.1700
Data Index: 2552793 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.3480. Min Act: -0.1700
Data Index: 2249280 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.3480. Min Act: -0.1700
Data Index: 6060270 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.3167. Min Act: -0.1700
Data Index: 5286127 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.3167. Min Act: -0.1700
Data Index: 1676835 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.3167. Min Act: -0.1700
Data Index: 4873924 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.3167. Min Act: -0.1700
Data Index: 6974662 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.2855. Min Act: -0.1700
Data Index: 2092096 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.2542. Min Act: -0.1700
Data Index: 8346112 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.2855. Min Act: -0.1700
Data Index: 5306184 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.2542. Min Act: -0.1700
Data Index: 616836 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6292. Min Range: -5.6292
Max Act: 5.2230. Min Act: -0.1700
Data Index: 4564532 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19