Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6366 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.5065. Min Act: -0.1700
Data Index: 4261389 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.4753. Min Act: -0.1700
Data Index: 5273078 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.3190. Min Act: -0.1700
Data Index: 6517301 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.3503. Min Act: -0.1700
Data Index: 3651027 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.2565. Min Act: -0.1700
Data Index: 3129834 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.2565. Min Act: -0.1700
Data Index: 3800588 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.1628. Min Act: -0.1700
Data Index: 1517713 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.1003. Min Act: -0.1700
Data Index: 2275870 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.1003. Min Act: -0.1700
Data Index: 5228102 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.1003. Min Act: -0.1700
Data Index: 1359444 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.1003. Min Act: -0.1700
Data Index: 7393508 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.0690. Min Act: -0.1700
Data Index: 6123486 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.0378. Min Act: -0.1700
Data Index: 8208015 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.0690. Min Act: -0.1700
Data Index: 1815391 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.0690. Min Act: -0.1700
Data Index: 3894793 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.0378. Min Act: -0.1700
Data Index: 6209641 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.0378. Min Act: -0.1700
Data Index: 8537627 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.0690. Min Act: -0.1700
Data Index: 5351887 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.0378. Min Act: -0.1700
Data Index: 3402377 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5065. Min Range: -6.5065
Max Act: 6.0065. Min Act: -0.1700
Data Index: 4541801 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19