Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5914 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.9284. Min Act: -0.1700
Data Index: 2728466 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.9284. Min Act: -0.1700
Data Index: 4130831 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.9284. Min Act: -0.1700
Data Index: 1045615 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.8659. Min Act: -0.1700
Data Index: 4313971 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.8346. Min Act: -0.1700
Data Index: 4971678 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.7409. Min Act: -0.1700
Data Index: 118574 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.7409. Min Act: -0.1700
Data Index: 2948776 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.7096. Min Act: -0.1700
Data Index: 7522248 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.7096. Min Act: -0.1700
Data Index: 7578825 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.7096. Min Act: -0.1700
Data Index: 4674192 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.7096. Min Act: -0.1700
Data Index: 4124248 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.7096. Min Act: -0.1700
Data Index: 7863476 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.6784. Min Act: -0.1700
Data Index: 5050896 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.6784. Min Act: -0.1700
Data Index: 4765672 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.6784. Min Act: -0.1700
Data Index: 2655726 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.6471. Min Act: -0.1700
Data Index: 1193136 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.6471. Min Act: -0.1700
Data Index: 2262942 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.6471. Min Act: -0.1700
Data Index: 4728006 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.6471. Min Act: -0.1700
Data Index: 4988256 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9284. Min Range: -5.9284
Max Act: 5.6471. Min Act: -0.1700
Data Index: 10027 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19