Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1365 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1368. Min Range: -6.1368
Max Act: 6.1368. Min Act: -0.1700
Data Index: 1587598 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1368. Min Range: -6.1368
Max Act: 6.0118. Min Act: -0.1700
Data Index: 7780913 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.8868. Min Act: -0.1700
Data Index: 4565401 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.8868. Min Act: -0.1700
Data Index: 4919571 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.8555. Min Act: -0.1700
Data Index: 8265528 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.8243. Min Act: -0.1700
Data Index: 7410863 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.7618. Min Act: -0.1700
Data Index: 3065055 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.7618. Min Act: -0.1700
Data Index: 5253106 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.7618. Min Act: -0.1700
Data Index: 3793280 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.7618. Min Act: -0.1700
Data Index: 3101055 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.7305. Min Act: -0.1700
Data Index: 3192014 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.7305. Min Act: -0.1700
Data Index: 6889235 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.6993. Min Act: -0.1700
Data Index: 2064351 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.6993. Min Act: -0.1700
Data Index: 764540 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.6993. Min Act: -0.1700
Data Index: 3191240 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.6680. Min Act: -0.1700
Data Index: 2208461 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.6680. Min Act: -0.1700
Data Index: 4607662 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.6680. Min Act: -0.1700
Data Index: 1381350 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.6368. Min Act: -0.1700
Data Index: 2826686 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1368. Min Range: -6.1368
Max Act: 5.6055. Min Act: -0.1700
Data Index: 2924807 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19